A volumetric method for building complex models from range images

By Brian Curless, Marc Levoy. 1996

Subfields: Computer Graphics and Computer-Aided Design, 3D Vision & Pose

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 3D Vision & Pose

Citations in the corpus

Occupancy Networks: Learning 3D Reconstruction in Function Space (2018, background): “For achieving sub-voxel precision, several works [12,42,60] have proposed to predict truncated signed distance ﬁelds (TSDF) [11] where each point in a 3D grid stores the truncated signed distance to the closest 3D surface point.”
ScanNet: Richly-Annotated 3D Reconstructions of Indoor Scenes (2017, background): “This de-sign goal has broad implications on the choices made at every step of the process.”
DeepSDF: Learning Continuous Signed Distance Functions for Shape Representation (2019, methodology): “This inherits from the success of fusion approaches that utilize a truncated SDF (TSDF), pioneered in [15, 37], to combine noisy depth maps into a single 3D model.”
Learning a Multi-View Stereo Machine (2017, methodology): “These depth maps can then be fused using a variety of different techniques [38, 8, 33, 59, 30].”
OctNetFusion: Learning Depth Fusion from Data (2017, methodology): “Volumetric Fusion: In their seminal work, Curless and Levoy [9] proposed to integrate range information across viewpoints by averaging truncated signed distance functions.”
Hierarchical Surface Prediction for 3D Object Reconstruction (2017, methodology): “The common methods can be broadly grouped as implicit volumetric reconstruction [7], [18], [19], [22], [38] or explicit mesh based [9], [12] approaches.”
Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis (2016, methodology): “All views are integrated into a shared volumetric grid using the volumetric fusion approach by Curless and Levoy [6], where the voxel grid’s extent is deﬁned by the model bounding box.”
FPNN: Field Probing Neural Networks for 3D Data (2016, background): “it can be approximated by truncated distance fields [5], which is widely used in real time scanning and can be compactly stored by voxel hashing [21], 2.”
Past, Present, and Future of Simultaneous Localization and Mapping: Toward the Robust-Perception Age (2016, neutral): “functions [39], signed-distance function [56], and truncated”
SCAPE: shape completion and animation of people (2005, methodology): “We used this scanner to construct full-body instance meshes by merging the four scan views [Curless and Levoy 1996] and subsampling the instances to about 50,000 triangles [Garland and Heckbert 1997].”
kPAM: KeyPoint Affordances for Category-Level Robotic Manipulation (2019, methodology): “From the robot’s forward kinematics, we know the camera pose corresponding to each image which allows us to use TSDF fusion [2] to obtain a dense 3D reconstruction.”
Discrete optimization of ray potentials for semantic 3D reconstruction (2015, background): “Posing the problem of dense 3D reconstruction as a volumetric segmentation was ﬁrst proposed in [7].”
Deep Marching Cubes: Learning Explicit Surface Representations (2018, background): “As ShapeNet models comprise interior faces such as car seats, we rendered depth images and applied TSDF fusion at a high resolution (128 × 128 × 128 voxels) for extracting clean meshes and occupancy grids.”
Fast geometric learning with symbolic matrices (2020, unknown): “We perform numerical experiments with random normal samples and freely available datasets: digits from Scikit-Learn [87], Stanford dragon [26], ShapeNet [19].”
VolumeDeform: Real-Time Volumetric Non-rigid Reconstruction (2016, methodology): “The two fundamental building blocks are a truncated signed distance (TSDF) function [23] for reconstruction of the shape in its initial, undeformed pose and a space deformation ﬁeld to track the deformations.”
Dense Depth Priors for Neural Radiance Fields from Sparse Input Views (2021, methodology): “These include classic techniques that fuse observed depths into a single 3D reconstruction, typically in the form of a truncated signed distance function [5, 15], as well as more recent techniques that train deep networks to operate over the sparsely observed geometry in 3D [7,8].”