Photorealistic Scene Reconstruction by Voxel Coloring

By S. M. Seitz, Charles R. Dyer. 1997

How researchers see this paper

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

Citations in the corpus

SurfaceNet: An End-to-End 3D Neural Network for Multiview Stereopsis (2017, background): “While earlier works like space carving [14, 22] mainly use a volumetric representation, current state-of-the-art MVS methods focus on depth map fusion algorithms [27, 4, 9], which have been shown to be more competitive in handling large datasets in practice.”
3D-R2N2: A Unified Approach for Single and Multi-view 3D Object Reconstruction (2016, background): “In order to circumvent issues related to large baselines or non-Lambertian surfaces, 3D volumetric reconstruction methods such as space carving [12,13,14,15] and their probabilistic extensions [16] have become popular.”
NeRF: Representing scenes as neural radiance ﬁelds for view synthesis (unknown): “For example, consider the canonical voxel-coloring approach by Seitz and Dyer [ 59 ].”
3D Reconstruction by Shadow Carving: Theory and Practical Evaluation (2007, unknown): “An alternative approach is photoconsistency , as introduced by the work of Seitz and Dyer (1997), Kutulakos and Seitz (1999) and numerous extensions and/or alternative formulations (Broadhurst and Cipolla, 2001; Bhotika et al., 2002; Szeliski and Golland, 1999; de Bonet and Viola, 1999; Eisert et…”
Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (2022, background): “Explicit representation includes voxels [5, 29] and triangular mesh [3, 4, 14], which are limited by the resolution.”
Manhattan-world stereo (2009, background): “While this assumption may seem to be overly restrictive, note that any scene can be arbitrarily-well approximated (to first order) by axis-aligned geometry, as in the case of a high resolution voxel grid [14, 17].”
Cascade Cost Volume for High-Resolution Multi-View Stereo and Stereo Matching (2019, methodology): “Multi-View Stereo According to the comprehensive survey [5], works in traditional muti-view stereo can be roughly categorised into volumetric methods [13, 14, 18, 33], which estimate the relationship between each voxel and surfaces; point cloud based methods [6, 19], which directly process 3D points”
Consistent Depth Maps Recovery from a Video Sequence (2009, background): “, voxel-based approaches [33], [45]) aim to build a 3D model for a single object and are usually not applicable to largescale sceneries due to the high computational complexity and memory space requirement.”
Image-based visual hulls (2000, methodology): “A more common method used to convert silhouette contours into visual hulls is volume carving [22] [8] [29] [19] [5] [27].”
Silhouette and stereo fusion for 3D object modeling (2003, unknown): “A third class of methods uses color consistency to carve a voxel volume [26, 17].”
A probabilistic framework for space carving (2001, background): “A third class of algorithms are the volumetric representations, which may use voxels [14, 13 , 9, 4], or level sets [6].”
Modelling dynamic scenes by registering multi-view image sequences (2005, methodology): “It motivates the multi-view photo-consistency measure used in voxel coloring [ 23 ], space carving [13], and in the deformable mesh method of [5].”