3DV 2021

110 papers
The 2021 edition of the International Conference on 3D Vision (3DV) featured 163 papers focusing on spatial intelligence and geometric modeling. Research themes centered on human-centric 3D vision, including perspective-aware pose estimation, template-free reconstruction of articulated objects, and neural occupancy representations for hands. Depth estimation was a prominent area of study, with work addressing temporal consistency in video and geometry-guided attention for self-supervised monocular depth learning. Methodological trends included coarse-to-fine refinement strategies for dense correspondence and the development of category-agnostic priors for universal 3D understanding. Data augmentation techniques, such as Mix3D for out-of-context scene processing, and advancements in neural radiance fields (NeRF) for object category modeling were also featured. Prolific contributors included Otmar Hilliges, Marc Pollefeys, and Luc Van Gool, among others. Additional research explored 3D surface super-resolution and occlusion-aware geometric consistency, reflecting a shift toward robust, self-supervised learning frameworks in 3D environments.

Top Research Directions

Research directions most represented by 3DV 2021 papers.

Cascaded Error Propagation in 2D to 3D Lifting 3
Overcoming Geometric Symmetry Priors in 3D Object Perception 2
Emergent Semantic Part Decomposition 2
Composite Loss Functions for Perceptual Image Restoration 2
Zero-Shot Geometric Generalization 2
Resolving Shape Radiance Ambiguity in Sparse View Reconstruction 2
Resolving Self Occlusion in Articulated Pose Estimation 2
Overcoming the Instability of Direct Coordinate Regression 1
Computational Spectral Reconstruction from Multiplexed Measurements 1
Stereo Matching for Asymmetric and Unbalanced Views 1
Multi-Chart Latent Spaces for Complex Data Topologies 1
Scale Equivariance through Bias Free Neural Architectures 1
Architectural Generalization Across 3D Perception Tasks 1
Sparse Control Graphs for Non-Rigid Object Modeling 1
Unsupervised Part Discovery and Semantic Alignment 1

Top Authors

AuthorPapers
Francesc Moreno-Noguer4
Otmar Hilliges4
Benjamin Busam3
Christian Theobalt3
Davide Scaramuzza3
Luc Van Gool3
Marc Pollefeys3
Martin R. Oswald3
Nassir Navab3
Renaud Marlet3
Siyu Tang3
Adnane Boukhayma2
Adrian Spurr2
Andrea Vedaldi2
Antonio Agudo2
Daniel Cremers2
Federico Tombari2
Florian Bernard2
Jun CEN2
Lingjie Liu2

Impactful Papers

Papers from 3DV 2021 that shaped research clusters.

Foundational

Influential

Papers

Title
Softmesh: Learning Probabilistic Mesh Connectivity via Image Supervision
Spectral Reconstruction and Disparity from Spatio-Spectrally Coded Light Fields via Multi-Task Deep Learning
Stochastic Neural Radiance Fields: Quantifying Uncertainty in Implicit 3D Representations
Synergy between 3DMM and 3D Landmarks for Accurate 3D Facial Geometry
Task-Generic Hierarchical Human Motion Prior using VAEs
TermiNeRF: Ray Termination Prediction for Efficient Neural Rendering
Towards Unconstrained Joint Hand-Object Reconstruction From RGB Videos
Unsupervised Monocular Depth Reconstruction of Non-Rigid Scenes
Visual Camera Re-Localization Using Graph Neural Networks and Relative Pose Supervision
Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments

« prev Page 3/3