Dynamic shape capture using multi-view photometric stereo

By Daniel Vlasic, P. Peers, Ilya Baran, Paul E. Debevec, Jovan Popovic, Szymon Rusinkiewicz, Wojciech Matusik. ACM Transactions on Graphics, 2009

322 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cb33ef9a2c7520d27c307ec4a8ea6e51146d2cd0

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 Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Panoptic Studio: A Massively Multiview System for Social Interaction Capture (2016, methodology): “[22] recovered detail by applying multi-view photometric stereo constraints using a system with 1,200 lights on a dome and eight cameras.”
PIFu: Pixel-Aligned Implicit Function for High-Resolution Clothed Human Digitization (2019, methodology): “More accurate geometries can be obtained using multi-view stereo constraints [55, 75, 65, 16] or using controlled illumination, such as multi-view photometric stereo techniques [62, 68].”
1 An End-to-End Framework for Evaluating Surface Reconstruction (2011, background): “Note that such acquisition systems are starting to gain popularity [Vlasic et al. 2009].”
Multi-View Mesh Reconstruction with Neural Deferred Shading (2022, unknown): “While fully neural approaches are general, both in terms of geometry and appearance, current methods exhibit excessive runtime, making them impractical for domains that handle a large number of objects or multi-view video ( e.g . of human performances [8,20,62,67,73]).”
ARCH: Animatable Reconstruction of Clothed Humans (2020, background): “There are multiple attempts to solve this task with video inputs [2, 3, 37, 1, 52], RGB-D data [53, 56] and in multi-view settings [5, 13, 14, 45, 46, 47, 48, 6].”
DeepHuman: 3D Human Reconstruction From a Single Image (2019, background): “Shape cues like silhouette, stereo and shading cues have been integrated to improve the reconstruction performance[47, 30, 58, 57, 55].”
PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction (2020, background): “Shape cues like silhou-ette, stereo and shading have been integrated to improve the reconstruction performance [17], [18], [19], [20], [21].”
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors (2021, background): “Although high-end volumetric capture systems [4, 13, 25, 5, 27, 36] based on dense camera rigs (up to 100 cameras [8]) and custom-designed lighting conditions [47, 14] can achieve high-quality reconstruction, they all suffer from complicated system setups and are limited to professional studio usage”
Total Capture: A 3D Deformation Model for Tracking Faces, Hands, and Bodies (2018, background): “Note that we differentiate markerless motion capture approaches, producing motion parameters as output, frommultiview performance capture approaches [56, 22] which aim to obtain detailed surface shapes by free-form mesh deformations.”
Tensor4D: Efficient Neural 4D Decomposition for High-Fidelity Dynamic Reconstruction and Rendering (2022, methodology): “There are various ways to capture and reconstruct the 3D dynamic scenes, involving methods based on silhouette [24, 54], stereo [30, 46], flow [17, 44, 70], segmentation [41, 42], and photometric [3, 20].”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, methodology): “Approaches have also emerged to recover geometric details using multi-view constraints [18–20] and photometric stereo [4, 21].”