We introduce a real-time deep learning-based face synthesis technology for photoreal AI-avatars, ... more We introduce a real-time deep learning-based face synthesis technology for photoreal AI-avatars, and demonstrate two novel applications. We showcase the first zero-shot real-time deepfake system allowing anyone to swap their faces with another subject. Then, we demonstrate how this technology can enable an AI-based photoreal virtual assistant.
Our main results in the paper demonstrate successful inference of high-fidelity texture maps from... more Our main results in the paper demonstrate successful inference of high-fidelity texture maps from unconstrained images. The input images have mostly low resolutions, nonfrontal faces, and the subjects are often captured in challenging lighting conditions. We provide additional results with pictures from the annotated faces-in-the-wild (AFW) dataset [9] to further demonstrate how photorealistic porelevel details can be synthesized using our deep learning approach. We visualize in Figure 7 the input, the intermediate low-frequency albedo map obtained using a linear PCA model, and the synthesized high-frequency albedo texture map. We also show several views of the final renderings using the Arnold renderer [11]. We refer to the accompanying video for additional rotating views of the resulting textured 3D face models.
We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a perso... more We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. While the input image can be of a smiling person or taken in extreme lighting conditions, our method can reliably produce a high-quality textured model of a person's face in neutral expression and skin textures under diffuse lighting condition. Cutting-edge 3D face reconstruction methods use non-linear morphable face models combined with GAN-based decoders to capture the likeness and details of a person but fail to produce neutral head models with unshaded albedo textures which is critical for creating relightable and animation-friendly avatars for integration in virtual environments. The key challenges for existing methods to work is the lack of training and ground truth data containing normalized 3D faces. We propose a two-stage approach to address this problem. First, we adopt a highly robust normalized 3D face generator by embedding a non-line...
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
for Creative Technologies input picture output albedo map rendering rendering (zoom) rendering (z... more for Creative Technologies input picture output albedo map rendering rendering (zoom) rendering (zoom) rendering Figure 1: We present an inference framework based on deep neural networks for synthesizing photorealistic facial texture along with 3D geometry from a single unconstrained image. We can successfully digitize historic figures that are no longer available for scanning and produce high-fidelity facial texture maps with mesoscopic skin details.
With the rising interest in personalized VR and gaming experiences comes the need to create high ... more With the rising interest in personalized VR and gaming experiences comes the need to create high quality 3D avatars that are both low-cost and variegated. Due to this, building dynamic avatars from a single unconstrained input image is becoming a popular application. While previous techniques that attempt this require multiple input images or rely on transferring dynamic facial appearance from a source actor, we are able to do so using only one 2D input image without any form of transfer from a source image. We achieve this using a new conditional Generative Adversarial Network design that allows fine-scale manipulation of any facial input image into a new expression while preserving its identity. Our photoreal avatar GAN (paGAN) can also synthesize the unseen mouth interior and control the eye-gaze direction of the output, as well as produce the final image from a novel viewpoint. The method is even capable of generating fully-controllable temporally stable video sequences, despite...
We present an end-to-end system for reconstructing complete watertight and textured models of mov... more We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals, using only three or four handheld sensors. The heart of our framework is a new pairwise registration algorithm that minimizes, using a particle swarm strategy, an alignment error metric based on mutual visibility and occlusion. We show that this algorithm reliably registers partial scans with as little as 15% overlap without requiring any initial correspondences, and outperforms alternative global registration algorithms. This registration algorithm allows us to reconstruct moving subjects from free-viewpoint video produced by consumer-grade sensors, without extensive sensor calibration, constrained capture volume, expensive arrays of cameras, or templates of the subject geometry.
In most realtime applications such as 3D games, in order to reduce the complexity of the scene be... more In most realtime applications such as 3D games, in order to reduce the complexity of the scene being rendered, objects are often made by simple and large primitives. Thus, the phenomenon of edge highlighting, which would require chamfering structures made by lots of small patches at the seaming, is absent and is often faked by "highlights" drawn on the texture. We proposed a realistic realtime rendering procedure for highlighting chamfering structures, or rounded edges, by considering specified edges as thin cylinders and obtained the intensity via integration. We derived a brief approximated formula generalized from Blinn's shadow model, and used a precomputed integration table to accelerate the render speed and reduce resources needed. The algorithm is implemented with shader language, and can be considered as a post-process on original result. Evaluation shows that the effect on rendering speed is limited even for scenes with large scale of vertices.
From angling smiles to duck faces, all kinds of facial expressions can be seen in selfies, portra... more From angling smiles to duck faces, all kinds of facial expressions can be seen in selfies, portraits, and Internet pictures. These photos are taken from various camera types, and under a vast range of angles and lighting conditions. We present a deep learning framework that can fully normalize unconstrained face images, i.e., remove perspective distortions, relight to an evenly lit environment, and predict a frontal and neutral face. Our method can produce a high resolution image while preserving important facial details and the likeness of the subject, along with the original background. We divide this ill-posed problem into three consecutive normalization steps, each using a different generative adversarial network that acts as an image generator. Perspective distortion removal is performed using a dense flow field predictor. A uniformly illuminated face is obtained using a lighting translation network, and the facial expression is neutralized using a generalized facial expression...
reference image reference hair model rendering results reference image rendering results referenc... more reference image reference hair model rendering results reference image rendering results reference hair model Fig. 1. We propose a real-time hair rendering method. Given a reference image, we can render a 3D hair model with the referenced color and lighting in real-time. Faces in this paper are obfuscated to avoid copyright infringement Abstract. We present an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines. Our deep learning approach does not require low-level parameter tuning nor ad-hoc asset design. Our method simply takes a strand-based 3D hair model as input and provides intuitive user-control for color and lighting through reference images. To handle the diversity of hairstyles and its appearance complexity, we disentangle hair structure, color, and illumination properties using a sequential GAN architecture and a semisupervised training approach. We also introduce an intermediate edge activation map to orientation field conversion step to ensure a successful CG-to-photoreal transition, while preserving the hair structures of the original input data. As we only require a feed-forward pass through the network, our rendering performs in real-time. We demonstrate the synthesis of photorealistic hair images on a wide range of intricate hairstyles and compare our technique with state-of-the-art hair rendering methods.
IEEE transactions on visualization and computer graphics, Jan 27, 2015
In this work we explore a support-induced structural organization of object parts. We introduce t... more In this work we explore a support-induced structural organization of object parts. We introduce the concept of support substructures, which are special subsets of object parts with support and stability. A bottom-up approach is proposed to identify such substructures in a support relation graph. We apply the derived high-level substructures to part-based shape reshuffling between models, resulting in nontrivial functionally plausible model variations that are difficult to achieve with symmetry-induced substructures by the state-of-the-art methods. We also show how to automatically or interactively turn a single input model to new functionally plausible shapes by structure rearrangement and synthesis, enabled by support substructures. To the best of our knowledge no single existing method has been designed for all these applications.
input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D ... more input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D avatar Fig. 1. We introduce an end-to-end framework for modeling a complete 3D avatar from a single input image for real-time rendering. We infer fully rigged textured faces models and polygonal strips for hair. Our flexible and efficient mesh-based hair representation is suitable for a wide range of hairstyles and can be readily integrated into existing real-time game engines. All of the illustrations are rendered in realtime in Unity. President Trump's picture is obtained from whitehouse.gov and Kim Jong-un's photograph was published in the Rodong Sinmun. The other celebrity pictures are used with permission from Getty Images. We present a fully automatic framework that digitizes a complete 3D head with hair from a single unconstrained image. Our system offers a practical and consumer-friendly end-to-end solution for avatar personalization in gaming and social VR applications. The reconstructed models include secondary components (eyes, teeth, tongue, and gums) and provide animation-friendly blendshapes and joint-based rigs. While the generated face is a high-quality textured mesh, we propose a versatile and efficient polygonal strips (polystrips) representation for the hair. Polystrips are suitable for an extremely wide range of hairstyles and textures and are compatible with existing game engines for real-time rendering. In addition to integrating state-of-the-art advances in facial shape modeling and appearance inference , we propose a novel single-view hair generation pipeline, based on * indicates equal contribution Permission to make digitalmodel and texture retrieval, shape refinement, and polystrip patching optimization. The performance of our hairstyle retrieval is enhanced using a deep convolutional neural network for semantic hair attribute classification. Our generated models are visually comparable to state-of-the-art game characters designed by professional artists. For real-time settings, we demonstrate the flexibility of polystrips in handling hairstyle variations, as opposed to conventional strand-based representations. We further show the effectiveness of our approach on a large number of images taken in the wild, and how compelling avatars can be easily created by anyone.
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Figure 1: We introduce a deep learning framework for computing dense correspondences between huma... more Figure 1: We introduce a deep learning framework for computing dense correspondences between human shapes in arbitrary, complex poses, and wearing varying clothing. Our approach can handle full 3D models as well as partial scans generated from a single depth map. The source and target shapes do not need to be the same subject, as highlighted in the left pair. Abstract We propose a deep learning approach for finding dense correspondences between 3D scans of people. Our method requires only partial geometric information in the form of two depth maps or partial reconstructed surfaces, works for humans in arbitrary poses and wearing any clothing, does not require the two people to be scanned from similar viewpoints , and runs in real time. We use a deep convolutional neural network to train a feature descriptor on depth map pixels, but crucially, rather than training the network to solve the shape correspondence problem directly, we train it to solve a body region classification problem, modified to increase the smoothness of the learned descriptors near region boundaries. This approach ensures that nearby points on the human body are nearby in feature space, and vice versa, rendering the feature descriptor suitable for computing dense correspondences between the scans. We validate our method on real and synthetic data for both clothed and unclothed humans, and show that our correspondences are more robust than is possible with state-of-the-art unsuper-vised methods, and more accurate than those found using methods that require full watertight 3D geometry.
HMD (CAD model) interior (CAD model) online operation RGB-D camera strain sensors foam liner faci... more HMD (CAD model) interior (CAD model) online operation RGB-D camera strain sensors foam liner facial performance capture Figure 1: To enable immersive face-to-face communication in virtual worlds, the facial expressions of a user have to be captured while wearing a virtual reality head-mounted display. Because the face is largely occluded by typical wearable displays, we have designed an HMD that combines ultra-thin strain sensors with a head-mounted RGB-D camera for real-time facial performance capture and animation. Abstract There are currently no solutions for enabling direct face-to-face interaction between virtual reality (VR) users wearing head-mounted displays (HMDs). The main challenge is that the headset obstructs a significant portion of a user's face, preventing effective facial capture with traditional techniques. To advance virtual reality as a next-generation communication platform, we develop a novel HMD that enables 3D facial performance-driven animation in real-time. Our wearable system uses ultra-thin flexible electronic materials that are mounted on the foam liner of the headset to measure surface strain signals corresponding to upper face expressions. These strain signals are combined with a head-mounted RGB-D camera to enhance the tracking in the mouth region and to account for inaccurate HMD placement. To map the input signals to a 3D face model, we perform a single-instance offline training session for each person. For reusable and accurate online operation, we propose a short calibration step to readjust the Gaussian mixture distribution of the mapping before each use. The resulting animations are visually on par with cutting-edge depth sensor-driven facial performance capture systems and hence, are suitable for social interactions in virtual worlds.
We present an end-to-end system for reconstructing complete watertight and textured models of mov... more We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals , using only three or four handheld sensors. The heart of our framework is a new pairwise registration algorithm that minimizes, using a particle swarm strategy, an alignment error metric based on mutual visibility and occlusion. We show that this algorithm reliably registers partial scans with as little as 15% overlap without requiring any initial correspondences, and outperforms alternative global registration algorithms. This registration algorithm allows us to reconstruct moving subjects from free-viewpoint video produced by consumer-grade sensors, without extensive sensor calibration, constrained capture volume, expensive arrays of cameras, or templates of the subject geometry.
We introduce a real-time deep learning-based face synthesis technology for photoreal AI-avatars, ... more We introduce a real-time deep learning-based face synthesis technology for photoreal AI-avatars, and demonstrate two novel applications. We showcase the first zero-shot real-time deepfake system allowing anyone to swap their faces with another subject. Then, we demonstrate how this technology can enable an AI-based photoreal virtual assistant.
Our main results in the paper demonstrate successful inference of high-fidelity texture maps from... more Our main results in the paper demonstrate successful inference of high-fidelity texture maps from unconstrained images. The input images have mostly low resolutions, nonfrontal faces, and the subjects are often captured in challenging lighting conditions. We provide additional results with pictures from the annotated faces-in-the-wild (AFW) dataset [9] to further demonstrate how photorealistic porelevel details can be synthesized using our deep learning approach. We visualize in Figure 7 the input, the intermediate low-frequency albedo map obtained using a linear PCA model, and the synthesized high-frequency albedo texture map. We also show several views of the final renderings using the Arnold renderer [11]. We refer to the accompanying video for additional rotating views of the resulting textured 3D face models.
We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a perso... more We introduce a highly robust GAN-based framework for digitizing a normalized 3D avatar of a person from a single unconstrained photo. While the input image can be of a smiling person or taken in extreme lighting conditions, our method can reliably produce a high-quality textured model of a person's face in neutral expression and skin textures under diffuse lighting condition. Cutting-edge 3D face reconstruction methods use non-linear morphable face models combined with GAN-based decoders to capture the likeness and details of a person but fail to produce neutral head models with unshaded albedo textures which is critical for creating relightable and animation-friendly avatars for integration in virtual environments. The key challenges for existing methods to work is the lack of training and ground truth data containing normalized 3D faces. We propose a two-stage approach to address this problem. First, we adopt a highly robust normalized 3D face generator by embedding a non-line...
2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017
for Creative Technologies input picture output albedo map rendering rendering (zoom) rendering (z... more for Creative Technologies input picture output albedo map rendering rendering (zoom) rendering (zoom) rendering Figure 1: We present an inference framework based on deep neural networks for synthesizing photorealistic facial texture along with 3D geometry from a single unconstrained image. We can successfully digitize historic figures that are no longer available for scanning and produce high-fidelity facial texture maps with mesoscopic skin details.
With the rising interest in personalized VR and gaming experiences comes the need to create high ... more With the rising interest in personalized VR and gaming experiences comes the need to create high quality 3D avatars that are both low-cost and variegated. Due to this, building dynamic avatars from a single unconstrained input image is becoming a popular application. While previous techniques that attempt this require multiple input images or rely on transferring dynamic facial appearance from a source actor, we are able to do so using only one 2D input image without any form of transfer from a source image. We achieve this using a new conditional Generative Adversarial Network design that allows fine-scale manipulation of any facial input image into a new expression while preserving its identity. Our photoreal avatar GAN (paGAN) can also synthesize the unseen mouth interior and control the eye-gaze direction of the output, as well as produce the final image from a novel viewpoint. The method is even capable of generating fully-controllable temporally stable video sequences, despite...
We present an end-to-end system for reconstructing complete watertight and textured models of mov... more We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals, using only three or four handheld sensors. The heart of our framework is a new pairwise registration algorithm that minimizes, using a particle swarm strategy, an alignment error metric based on mutual visibility and occlusion. We show that this algorithm reliably registers partial scans with as little as 15% overlap without requiring any initial correspondences, and outperforms alternative global registration algorithms. This registration algorithm allows us to reconstruct moving subjects from free-viewpoint video produced by consumer-grade sensors, without extensive sensor calibration, constrained capture volume, expensive arrays of cameras, or templates of the subject geometry.
In most realtime applications such as 3D games, in order to reduce the complexity of the scene be... more In most realtime applications such as 3D games, in order to reduce the complexity of the scene being rendered, objects are often made by simple and large primitives. Thus, the phenomenon of edge highlighting, which would require chamfering structures made by lots of small patches at the seaming, is absent and is often faked by "highlights" drawn on the texture. We proposed a realistic realtime rendering procedure for highlighting chamfering structures, or rounded edges, by considering specified edges as thin cylinders and obtained the intensity via integration. We derived a brief approximated formula generalized from Blinn's shadow model, and used a precomputed integration table to accelerate the render speed and reduce resources needed. The algorithm is implemented with shader language, and can be considered as a post-process on original result. Evaluation shows that the effect on rendering speed is limited even for scenes with large scale of vertices.
From angling smiles to duck faces, all kinds of facial expressions can be seen in selfies, portra... more From angling smiles to duck faces, all kinds of facial expressions can be seen in selfies, portraits, and Internet pictures. These photos are taken from various camera types, and under a vast range of angles and lighting conditions. We present a deep learning framework that can fully normalize unconstrained face images, i.e., remove perspective distortions, relight to an evenly lit environment, and predict a frontal and neutral face. Our method can produce a high resolution image while preserving important facial details and the likeness of the subject, along with the original background. We divide this ill-posed problem into three consecutive normalization steps, each using a different generative adversarial network that acts as an image generator. Perspective distortion removal is performed using a dense flow field predictor. A uniformly illuminated face is obtained using a lighting translation network, and the facial expression is neutralized using a generalized facial expression...
reference image reference hair model rendering results reference image rendering results referenc... more reference image reference hair model rendering results reference image rendering results reference hair model Fig. 1. We propose a real-time hair rendering method. Given a reference image, we can render a 3D hair model with the referenced color and lighting in real-time. Faces in this paper are obfuscated to avoid copyright infringement Abstract. We present an adversarial network for rendering photorealistic hair as an alternative to conventional computer graphics pipelines. Our deep learning approach does not require low-level parameter tuning nor ad-hoc asset design. Our method simply takes a strand-based 3D hair model as input and provides intuitive user-control for color and lighting through reference images. To handle the diversity of hairstyles and its appearance complexity, we disentangle hair structure, color, and illumination properties using a sequential GAN architecture and a semisupervised training approach. We also introduce an intermediate edge activation map to orientation field conversion step to ensure a successful CG-to-photoreal transition, while preserving the hair structures of the original input data. As we only require a feed-forward pass through the network, our rendering performs in real-time. We demonstrate the synthesis of photorealistic hair images on a wide range of intricate hairstyles and compare our technique with state-of-the-art hair rendering methods.
IEEE transactions on visualization and computer graphics, Jan 27, 2015
In this work we explore a support-induced structural organization of object parts. We introduce t... more In this work we explore a support-induced structural organization of object parts. We introduce the concept of support substructures, which are special subsets of object parts with support and stability. A bottom-up approach is proposed to identify such substructures in a support relation graph. We apply the derived high-level substructures to part-based shape reshuffling between models, resulting in nontrivial functionally plausible model variations that are difficult to achieve with symmetry-induced substructures by the state-of-the-art methods. We also show how to automatically or interactively turn a single input model to new functionally plausible shapes by structure rearrangement and synthesis, enabled by support substructures. To the best of our knowledge no single existing method has been designed for all these applications.
input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D ... more input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D avatar input image face mesh and hair polystrips 3D avatar Fig. 1. We introduce an end-to-end framework for modeling a complete 3D avatar from a single input image for real-time rendering. We infer fully rigged textured faces models and polygonal strips for hair. Our flexible and efficient mesh-based hair representation is suitable for a wide range of hairstyles and can be readily integrated into existing real-time game engines. All of the illustrations are rendered in realtime in Unity. President Trump's picture is obtained from whitehouse.gov and Kim Jong-un's photograph was published in the Rodong Sinmun. The other celebrity pictures are used with permission from Getty Images. We present a fully automatic framework that digitizes a complete 3D head with hair from a single unconstrained image. Our system offers a practical and consumer-friendly end-to-end solution for avatar personalization in gaming and social VR applications. The reconstructed models include secondary components (eyes, teeth, tongue, and gums) and provide animation-friendly blendshapes and joint-based rigs. While the generated face is a high-quality textured mesh, we propose a versatile and efficient polygonal strips (polystrips) representation for the hair. Polystrips are suitable for an extremely wide range of hairstyles and textures and are compatible with existing game engines for real-time rendering. In addition to integrating state-of-the-art advances in facial shape modeling and appearance inference , we propose a novel single-view hair generation pipeline, based on * indicates equal contribution Permission to make digitalmodel and texture retrieval, shape refinement, and polystrip patching optimization. The performance of our hairstyle retrieval is enhanced using a deep convolutional neural network for semantic hair attribute classification. Our generated models are visually comparable to state-of-the-art game characters designed by professional artists. For real-time settings, we demonstrate the flexibility of polystrips in handling hairstyle variations, as opposed to conventional strand-based representations. We further show the effectiveness of our approach on a large number of images taken in the wild, and how compelling avatars can be easily created by anyone.
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016
Figure 1: We introduce a deep learning framework for computing dense correspondences between huma... more Figure 1: We introduce a deep learning framework for computing dense correspondences between human shapes in arbitrary, complex poses, and wearing varying clothing. Our approach can handle full 3D models as well as partial scans generated from a single depth map. The source and target shapes do not need to be the same subject, as highlighted in the left pair. Abstract We propose a deep learning approach for finding dense correspondences between 3D scans of people. Our method requires only partial geometric information in the form of two depth maps or partial reconstructed surfaces, works for humans in arbitrary poses and wearing any clothing, does not require the two people to be scanned from similar viewpoints , and runs in real time. We use a deep convolutional neural network to train a feature descriptor on depth map pixels, but crucially, rather than training the network to solve the shape correspondence problem directly, we train it to solve a body region classification problem, modified to increase the smoothness of the learned descriptors near region boundaries. This approach ensures that nearby points on the human body are nearby in feature space, and vice versa, rendering the feature descriptor suitable for computing dense correspondences between the scans. We validate our method on real and synthetic data for both clothed and unclothed humans, and show that our correspondences are more robust than is possible with state-of-the-art unsuper-vised methods, and more accurate than those found using methods that require full watertight 3D geometry.
HMD (CAD model) interior (CAD model) online operation RGB-D camera strain sensors foam liner faci... more HMD (CAD model) interior (CAD model) online operation RGB-D camera strain sensors foam liner facial performance capture Figure 1: To enable immersive face-to-face communication in virtual worlds, the facial expressions of a user have to be captured while wearing a virtual reality head-mounted display. Because the face is largely occluded by typical wearable displays, we have designed an HMD that combines ultra-thin strain sensors with a head-mounted RGB-D camera for real-time facial performance capture and animation. Abstract There are currently no solutions for enabling direct face-to-face interaction between virtual reality (VR) users wearing head-mounted displays (HMDs). The main challenge is that the headset obstructs a significant portion of a user's face, preventing effective facial capture with traditional techniques. To advance virtual reality as a next-generation communication platform, we develop a novel HMD that enables 3D facial performance-driven animation in real-time. Our wearable system uses ultra-thin flexible electronic materials that are mounted on the foam liner of the headset to measure surface strain signals corresponding to upper face expressions. These strain signals are combined with a head-mounted RGB-D camera to enhance the tracking in the mouth region and to account for inaccurate HMD placement. To map the input signals to a 3D face model, we perform a single-instance offline training session for each person. For reusable and accurate online operation, we propose a short calibration step to readjust the Gaussian mixture distribution of the mapping before each use. The resulting animations are visually on par with cutting-edge depth sensor-driven facial performance capture systems and hence, are suitable for social interactions in virtual worlds.
We present an end-to-end system for reconstructing complete watertight and textured models of mov... more We present an end-to-end system for reconstructing complete watertight and textured models of moving subjects such as clothed humans and animals , using only three or four handheld sensors. The heart of our framework is a new pairwise registration algorithm that minimizes, using a particle swarm strategy, an alignment error metric based on mutual visibility and occlusion. We show that this algorithm reliably registers partial scans with as little as 15% overlap without requiring any initial correspondences, and outperforms alternative global registration algorithms. This registration algorithm allows us to reconstruct moving subjects from free-viewpoint video produced by consumer-grade sensors, without extensive sensor calibration, constrained capture volume, expensive arrays of cameras, or templates of the subject geometry.
Uploads
Papers by Cosimo Wei