AAAI 2023 accepted papers on 3D vision
49 of the 2,023 papers accepted at AAAI 2023 (2.4%) are on 3D vision, compared with 2.7% at AAAI 2022. They fall into 5 topics.
See AAAI 2023 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Depth and stereo · 15 papers
- BEVDepth: Acquisition of Reliable Depth for Multi-View 3D Object Detection (757 citations)
- BEVStereo: Enhancing Depth Estimation in Multi-View 3D Object Detection with Temporal Stereo (216 citations)
- Efficient Edge-Preserving Multi-View Stereo Network for Depth Estimation (39 citations)
- ConvMatch: Rethinking Network Design for Two-View Correspondence Learning (36 citations)
- DesNet: Decomposed Scale-Consistent Network for Unsupervised Depth Completion (28 citations)
- Crafting Monocular Cues and Velocity Guidance for Self-Supervised Multi-Frame Depth Learning (27 citations)
- Take Your Model Further: A General Post-refinement Network for Light Field Disparity Estimation via BadPix Correction (20 citations)
- Rethinking Disparity: A Depth Range Free Multi-View Stereo Based on Disparity (19 citations)
- RobustLoc: Robust Camera Pose Regression in Challenging Driving Environments (19 citations)
- Learning to Super-resolve Dynamic Scenes for Neuromorphic Spike Camera (18 citations)
- Learning Continuous Depth Representation via Geometric Spatial Aggregator (17 citations)
- Self-Supervised Joint Dynamic Scene Reconstruction and Optical Flow Estimation for Spiking Camera (13 citations)
and 3 more in the interactive map.
Human pose estimation · 13 papers
- Pose-Oriented Transformer with Uncertainty-Guided Refinement for 2D-to-3D Human Pose Estimation (74 citations)
- CEE-Net: Complementary End-to-End Network for 3D Human Pose Generation and Estimation (46 citations)
- Two Heads Are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation (36 citations)
- Weakly Supervised 3D Multi-Person Pose Estimation for Large-Scale Scenes Based on Monocular Camera and Single LiDAR (29 citations)
- Tracking and Reconstructing Hand Object Interactions from Point Cloud Sequences in the Wild (16 citations)
- IKOL: Inverse Kinematics Optimization Layer for 3D Human Pose and Shape Estimation via Gauss-Newton Differentiation (14 citations)
- Progressive Multi-View Human Mesh Recovery with Self-Supervision (14 citations)
- HybridCap: Inertia-Aid Monocular Capture of Challenging Human Motions (13 citations)
- Delving Deep into Pixel Alignment Feature for Accurate Multi-View Human Mesh Recovery (12 citations)
- 3D Human Pose Lifting with Grid Convolution (8 citations)
- Pose-Guided 3D Human Generation in Indoor Scene (4 citations)
- Inter-image Contrastive Consistency for Multi-Person Pose Estimation (3 citations)
and 1 more in the interactive map.
3D generation · 11 papers
- Cross-View Geo-Localization via Learning Disentangled Geometric Layout Correspondence (79 citations)
- READ: Large-Scale Neural Scene Rendering for Autonomous Driving (56 citations)
- Safe Multi-View Deep Classification (33 citations)
- Simple and Effective Synthesis of Indoor 3D Scenes (19 citations)
- Occupancy Planes for Single-View RGB-D Human Reconstruction (11 citations)
- LagNet: Deep Lagrangian Mechanics for Plug-and-Play Molecular Representation Learning (6 citations)
- 3D Assembly Completion (5 citations)
- Erratum to: 3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation (2 citations)
- Photogrammetry and VR for Comparing 2D and Immersive Linguistic Data Collection (Student Abstract)
- Scalable Spatial Memory for Scene Rendering and Navigation
- 3D-TOGO: Towards Text-Guided Cross-Category 3D Object Generation
Face and shape · 5 papers
- RAFaRe: Learning Robust and Accurate Non-parametric 3D Face Reconstruction from Pseudo 2D&3D Pairs (9 citations)
- AudioEar: Single-View Ear Reconstruction for Personalized Spatial Audio (4 citations)
- What Does Your Face Sound Like? 3D Face Shape towards Voice (4 citations)
- JR2Net: Joint Monocular 3D Face Reconstruction and Reenactment (3 citations)
- Neural Implicit Surface Reconstruction from Noisy Camera Observations (Student Abstract)
NeRF and radiance fields · 5 papers
- PDRF: Progressively Deblurring Radiance Field for Fast Scene Reconstruction from Blurry Images (27 citations)
- TinyNeRF: Towards 100 x Compression of Voxel Radiance Fields (16 citations)
- One Is All: Bridging the Gap between Neural Radiance Fields Architectures with Progressive Volume Distillation (15 citations)
- Bidirectional Optical Flow NeRF: High Accuracy and High Quality under Fewer Views (8 citations)
- Semantic 3D-Aware Portrait Synthesis and Manipulation Based on Compositional Neural Radiance Field (6 citations)