Image-based visual hulls

By Wojciech Matusik, Chris Buehler, Ramesh Raskar, Steven J. Gortler, Leonard McMillan. 2000

1,086 citations recorded by the source corpus.

Subfields: Computer Graphics and Computer-Aided Design, 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 Computer Graphics and Computer-Aided Design

In Computer Vision and Pattern Recognition

Citations in the corpus

Multi-view Supervision for Single-View Reconstruction via Differentiable Ray Consistency (2017, background): “Techniques based on this concept [2, 24] can obtain reconstructions of objects by space carving using multiple available views.”
High performance imaging using large camera arrays (2005, methodology): “Another use for multiple views is view interpolation to create the illusion of a smoothly moving virtual camera in a static or dynamic scene [Levoy and Hanrahan 1996; Gortler et al. 1996; Rander et al. 1997; Matusik et al. 2000].”
Free-Viewpoint Video of Human Actors Using Multiple Handheld Kinects (2013, background): “On the one side, there are multi-view stereo [1], [2], [3], shape from silhouette [4], [5] and surface deformation approaches [6], [7] which reconstruct time varying geometry and texture of human actors from multi-view video.”
Real-time consensus-based scene reconstruction using commodity graphics hardware (2002, methodology): “presented an efficient method for real-time rendering of a dynamic scene [21].”
Panoptic Studio: A Massively Multiview System for Social Interaction Capture (2016, background): “A number of systems were subsequently proposed to produce realtime virtualizations [18], [19], [20], [21].”
ShapeCodes: Self-supervised Feature Learning by Lifting Views to Viewgrids (2017, background): “Image-based models for object shape (implicitly) intersect silhouette images to carve a visual hull [42, 43].”
Weakly Supervised 3D Reconstruction with Adversarial Constraint (2017, methodology): “The silhouette is used to carve out spaces analogous to voxel carving [25, 39, 28] and to generate the visual hull.”
Soft Rasterizer: A Differentiable Renderer for Image-Based 3D Reasoning (2019, neutral): “key points/contours [3, 36, 27, 33] or shape/appearance priors [1, 29, 6, 24, 50].”
Survey of image-based representations and compression techniques (2003, background): “The image-based visual hull [ 54 ] is another geometry proxy that can be constructed and updated in real time.”
Urban Radiance Fields (2021, positive): “This line of sight information has been a key ingredient in “volume carving” techniques [12, 27,41].”
High-quality video view interpolation using a layered representation (2004, methodology): “Matusik et al. [2000] use the images from four calibrated FireWire cameras ( 256 × 256 ) to compute and shade visual hulls.”
HumanNeRF: Free-viewpoint Rendering of Moving People from Monocular Video (2022, background): “This problem – free-viwepoint rendering of a moving subject – is a longstanding research challenge, as it involves synthesizing previously unseen camera views while accounting for cloth folds, hair movement, and complex body poses [5, 6, 15, 18, 27, 38, 59, 65].”
Deep Volumetric Video From Very Sparse Multi-view Performance Capture (2018, background): “Further progresses have been made to the visual-hull-based viewing experience [9], smoothing the geometry with fewer cameras [16], and real-time performance [17].”
Free-viewpoint video of human actors (2003, methodology): “…presented in the Computer Graphics community typically involve the explicit reconstruction of scene geometry from the images at every time instant [Matusik et al. 2001; Matusik et al. 2000; Moezzi et al. 1997] without using a priori model information and explicit representation of motion data.”