NeurIPS 2022 accepted papers on 3D vision
94 of the 2,901 papers accepted at NeurIPS 2022 (3.2%) are on 3D vision, compared with 2.4% at NeurIPS 2021. They fall into 5 topics.
See NeurIPS 2022 in the interactive map
Submitting to NeurIPS? Checklist →
Working on something in this area? Describe your idea in scime atlas to see the closest papers by meaning and how crowded the spot has become.
Topics and papers
Face and shape · 35 papers
- GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images (186 citations)
- Geo-Neus: Geometry-Consistent Neural Implicit Surfaces Learning for Multi-view Reconstruction (81 citations)
- EpiGRAF: Rethinking training of 3D GANs (53 citations)
- HF-NeuS: Improved Surface Reconstruction Using High-Frequency Details (47 citations)
- Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising (38 citations)
- TANGO: Text-driven Photorealistic and Robust 3D Stylization via Lighting Decomposition (33 citations)
- ShapeCrafter: A Recursive Text-Conditioned 3D Shape Generation Model (26 citations)
- 3DILG: Irregular Latent Grids for 3D Generative Modeling (22 citations)
- AniFaceGAN: Animatable 3D-Aware Face Image Generation for Video Avatars (21 citations)
- Controllable 3D Face Synthesis with Conditional Generative Occupancy Fields (16 citations)
- LASSIE: Learning Articulated Shapes from Sparse Image Ensemble via 3D Part Discovery (15 citations)
- FOF: Learning Fourier Occupancy Field for Monocular Real-time Human Reconstruction (13 citations)
and 23 more in the interactive map.
3D generation · 18 papers
- GAUDI: A Neural Architect for Immersive 3D Scene Generation (55 citations)
- Model-Based Imitation Learning for Urban Driving (32 citations)
- HUMANISE: Language-conditioned Human Motion Generation in 3D Scenes (22 citations)
- SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning (22 citations)
- Learning Neural Acoustic Fields (18 citations)
- Object Scene Representation Transformer (11 citations)
- Zero-Shot 3D Drug Design by Sketching and Generating (8 citations)
- IKEA-Manual: Seeing Shape Assembly Step by Step (7 citations)
- AnimeRun: 2D Animation Visual Correspondence from Open Source 3D Movies (6 citations)
- 3D Concept Grounding on Neural Fields (5 citations)
- Learning Viewpoint-Agnostic Visual Representations by Recovering Tokens in 3D Space (5 citations)
- Hilbert Distillation for Cross-Dimensionality Networks (3 citations)
and 6 more in the interactive map.
Depth and stereo · 15 papers
- MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Surface Reconstruction (166 citations)
- Monocular Dynamic View Synthesis: A Reality Check (28 citations)
- Amortized Inference for Heterogeneous Reconstruction in Cryo-EM (23 citations)
- Neural Surface Reconstruction of Dynamic Scenes with Monocular RGB-D Camera (19 citations)
- WT-MVSNet: Window-based Transformers for Multi-view Stereo (17 citations)
- CroCo: Self-Supervised Pre-training for 3D Vision Tasks by Cross-View Completion (16 citations)
- S$^3$-NeRF: Neural Reflectance Field from Shading and Shadow under a Single Viewpoint (11 citations)
- FourierNets enable the design of highly non-local optical encoders for computational imaging (10 citations)
- Hierarchical Normalization for Robust Monocular Depth Estimation (8 citations)
- SCONE: Surface Coverage Optimization in Unknown Environments by Volumetric Integration (4 citations)
- Self-supervised surround-view depth estimation with volumetric feature fusion (2 citations)
- FlyView: a bio-informed optical flow truth dataset for visual navigation using panoramic stereo vision (1 citation)
and 3 more in the interactive map.
Human pose estimation · 13 papers
- Category-Level 6D Object Pose Estimation in the Wild: A Semi-Supervised Learning Approach and A New Dataset (29 citations)
- OnePose++: Keypoint-Free One-Shot Object Pose Estimation without CAD Models (29 citations)
- mRI: Multi-modal 3D Human Pose Estimation Dataset using mmWave, RGB-D, and Inertial Sensors (27 citations)
- APT-36K: A Large-scale Benchmark for Animal Pose Estimation and Tracking (21 citations)
- Embodied Scene-aware Human Pose Estimation (19 citations)
- DART: Articulated Hand Model with Diverse Accessories and Rich Textures (18 citations)
- AutoLink: Self-supervised Learning of Human Skeletons and Object Outlines by Linking Keypoints (11 citations)
- Benchmarking and Analyzing 3D Human Pose and Shape Estimation Beyond Algorithms (8 citations)
- Bringing Image Scene Structure to Video via Frame-Clip Consistency of Object Tokens (8 citations)
- Contact-aware Human Motion Forecasting (7 citations)
- Heatmap Distribution Matching for Human Pose Estimation (7 citations)
- Multiview Human Body Reconstruction from Uncalibrated Cameras (2 citations)
and 1 more in the interactive map.
NeRF and radiance fields · 13 papers
- Decomposing NeRF for Editing via Feature Field Distillation (102 citations)
- VoxGRAF: Fast 3D-Aware Image Synthesis with Sparse Voxel Grids (53 citations)
- DeVRF: Fast Deformable Voxel Radiance Fields for Dynamic Scenes (49 citations)
- Generative Neural Articulated Radiance Fields (41 citations)
- SAMURAI: Shape And Material from Unconstrained Real-world Arbitrary Image collections (38 citations)
- Compressible-composable NeRF via Rank-residual Decomposition (37 citations)
- Streaming Radiance Fields for 3D Video Synthesis (25 citations)
- Coordinates Are NOT Lonely - Codebook Prior Helps Implicit Neural 3D representations (6 citations)
- Improving 3D-aware Image Synthesis with A Geometry-aware Discriminator (6 citations)
- Unsupervised Multi-View Object Segmentation Using Radiance Field Propagation (6 citations)
- PeRFception: Perception using Radiance Fields (5 citations)
- Neural Transmitted Radiance Fields
and 1 more in the interactive map.
