Deep Volumetric Video From Very Sparse Multi-view Performance Capture

By Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing, Chloe LeGendre, Linjie Luo, Chongyang Ma, Hao Li. 2018

128 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning Implicit Fields for Generative Shape Modeling (2018, background): “[21] also trains a network to perform binary classification, like IM-NET.”
Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era (2019, background): “[121], which takes multiple RGB views and their corresponding camera calibra-”
Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning (2019, background): “With the availability of large-scale 3D shape dataset [5], learning-based approaches [45, 12, 15] are able to consider single or few images thanks to the shape prior learned from the data.”
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization (2019, background): “While [26] also utilize local features, due to the lack of 3D-aware feature fusion mechanism, their approach is unable to reason 3D shapes from a single-view.”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, methodology): “To perform full-body 3D reconstruction, currently available methods require the fusion of multiview images [7, 29, 22] or multiple temporal images [2] of the target.”
Non-Rigid Neural Radiance Fields: Reconstruction and Novel View Synthesis of a Dynamic Scene From Monocular Video (2020, unknown): “By using active depth cameras and such fusion-type reconstruction, dynamic scene capture and novel viewpoint rendering from a low number of cameras or a single camera were shown [96, 81, 25, 97].”
Texture Fields: Learning Texture Representations in Function Space (2019, background): “Several works [6, 17, 25, 28] proposed to formulate 3D reconstruction as learning a continuous occupancy function or a signeddistance field in 3D space, parameterized via a neural network.”
Soft Rasterizer: Differentiable Rendering for Unsupervised Single-View Mesh Reconstruction (2019, unknown): “d ground-truth data. To simplify the learning problem, some works reconstruct 3D shape via predicting intermediate 2.5D representations, such as depth map [43, 7, 25], visual hull [32], implicit ﬁeld [15], displacement map [16] or normal map [1, 36, 50]. When considering reconstructing 3D shape, vox”
Neural 3D Video Synthesis from Multi-view Video (2021, unknown): “[22] Zeng Huang, Tianye Li, Weikai Chen, Yajie Zhao, Jun Xing,”
Neural Body: Implicit Neural Representations with Structured Latent Codes for Novel View Synthesis of Dynamic Humans (2020, background): “[23, 47] propose multi-view reconstruction networks, but they do not release the pre-trained model, so we do not compare with them.”
Occupancy Flow: 4D Reconstruction by Learning Particle Dynamics (2019, background): “In particular, recent continuous representations [13, 22, 28, 38, 39,46,56,72] achieve impressive results at limited memory costs.”
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction (2020, methodology): “In order to reduce the difﬁculty of system setup, human model reconstruction from sparse camera views has recently been investigated by using CNNs for learning silhouette cues [27] and stereo cues [28].”
Learning to Infer Implicit Surfaces without 3D Supervision (2019, background): “Recent works [22, 5, 6, 7, 8, 23] have shown promising results on supervised learning for 3D shape inference based on implicit representations.”
BEHAVE: Dataset and Method for Tracking Human Object Interactions (2022, background): “…humans from monocular RGB data [12, 29, 31, 41, 43, 44, 58, 59, 64, 87] and under multiple views [37–40 , 62] Following the success of pixel-aligned implicit function learning [64, 65], recent methods can capture human performance from sparse [38, 80] or even a single RGB camera [47,48].”
Unsupervised Learning of 3D Object Categories from Videos in the Wild (2021, methodology): “Recent works, [20, 47, 48, 66, 61] utilize sampled perpixel encodings similar to us.”
Differentiable Volumetric Rendering: Learning Implicit 3D Representations Without 3D Supervision (2019, methodology): “the representation they use as voxel-based [8, 13, 19, 61, 64, 73, 82, 83], pointbased [2, 17, 31, 40, 77, 85], mesh-based [24, 32, 41, 55, 80], or implicit representations [3, 12, 22, 30, 48, 49, 56, 66, 81].”