TPAMI 2023 papers on 3D vision
82 of the 664 papers published in TPAMI 2023 (12.3%) are on 3D vision, compared with 9.4% at TPAMI 2022. They fall into 5 topics.
See TPAMI 2023 in the interactive map
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
Depth and stereo · 31 papers
- Unifying Flow, Stereo and Depth Estimation (302 citations)
- Monocular Depth Estimation: A Thorough Review (135 citations)
- SC-DepthV3: Robust Self-Supervised Monocular Depth Estimation for Dynamic Scenes (119 citations)
- PDC-Net+: Enhanced Probabilistic Dense Correspondence Network (105 citations)
- SDV-LOAM: Semi-Direct Visual–LiDAR Odometry and Mapping (72 citations)
- Hybrid High Dynamic Range Imaging fusing Neuromorphic and Conventional Images (47 citations)
- Booster: A Benchmark for Depth From Images of Specular and Transparent Surfaces (39 citations)
- OPAL: Occlusion Pattern Aware Loss for Unsupervised Light Field Disparity Estimation (38 citations)
- Hong Kong World: Leveraging Structural Regularity for Line-based SLAM (33 citations)
- Coarse-to-Fine Multi-Scene Pose Regression With Transformers (30 citations)
- A Study on the Generality of Neural Network Structures for Monocular Depth Estimation (27 citations)
- SPDET: Edge-Aware Self-Supervised Panoramic Depth Estimation Transformer With Spherical Geometry (26 citations)
and 19 more in the interactive map.
Face and shape · 19 papers
- FaceScape: 3D Facial Dataset and Benchmark for Single-View 3D Face Reconstruction (72 citations)
- Fast-SNARF: A Fast Deformer for Articulated Neural Fields (65 citations)
- Face Forgery Detection by 3D Decomposition and Composition Search (45 citations)
- Implicit Neural Representations With Structured Latent Codes for Human Body Modeling (36 citations)
- Fast and Robust Non-Rigid Registration Using Accelerated Majorization-Minimization (33 citations)
- Monocular 3D Fingerprint Reconstruction and Unwarping (32 citations)
- DaGAN++: Depth-Aware Generative Adversarial Network for Talking Head Video Generation (27 citations)
- Free-HeadGAN: Neural Talking Head Synthesis With Explicit Gaze Control (26 citations)
- Progressive Learning of 3D Reconstruction Network From 2D GAN Data (19 citations)
- CGOF++: Controllable 3D Face Synthesis With Conditional Generative Occupancy Fields (17 citations)
- DreamStone: Image as a Stepping Stone for Text-Guided 3D Shape Generation (17 citations)
- CIPS-3D++: End-to-End Real-Time High-Resolution 3D-Aware GANs for GAN Inversion and Stylization (12 citations)
and 7 more in the interactive map.
Human pose estimation · 15 papers
- ViTPose++: Vision Transformer for Generic Body Pose Estimation (217 citations)
- Recovering 3D Human Mesh From Monocular Images: A Survey (192 citations)
- PyMAF-X: Towards Well-Aligned Full-Body Model Regression From Monocular Images (166 citations)
- Consistent 3D Hand Reconstruction in Video via Self-Supervised Learning (85 citations)
- Convolutional Cross-View Pose Estimation (49 citations)
- Bailando ++: 3D Dance GPT With Choreographic Memory (37 citations)
- Learning to Augment Poses for 3D Human Pose Estimation in Images and Videos (31 citations)
- NOPE-SAC: Neural One-Plane RANSAC for Sparse-View Planar 3D Reconstruction (29 citations)
- Hierarchical Attention-Based Age Estimation and Bias Analysis (28 citations)
- Bias-Compensated Integral Regression for Human Pose Estimation (25 citations)
- Unsupervised 3D Pose Transfer With Cross Consistency and Dual Reconstruction (25 citations)
- SMPLer: Taming Transformers for Monocular 3D Human Shape and Pose Estimation (22 citations)
and 3 more in the interactive map.
3D generation · 10 papers
- SceneDreamer: Unbounded 3D Scene Generation From 2D Image Collections (73 citations)
- SceneHGN: Hierarchical Graph Networks for 3D Indoor Scene Generation With Fine-Grained Geometry (69 citations)
- TextSLAM: Visual SLAM With Semantic Planar Text Features (44 citations)
- Toward Human-Like Grasp: Functional Grasp by Dexterous Robotic Hand Via Object-Hand Semantic Representation (35 citations)
- Compositional Scene Representation Learning via Reconstruction: A Survey (31 citations)
- Synthesis of Multi-View 3D Fingerprints to Advance Contactless Fingerprint Identification (29 citations)
- View Synthesis of Dynamic Scenes Based on Deep 3D Mask Volume (26 citations)
- Fine Detailed Texture Learning for 3D Meshes With Generative Models (24 citations)
- 3D Visual Saliency: An Independent Perceptual Measure or a Derivative of 2D Image Saliency? (20 citations)
- Content-Aware Warping for View Synthesis (16 citations)
NeRF and radiance fields · 7 papers
- StructNeRF: Neural Radiance Fields for Indoor Scenes With Structural Hints (33 citations)
- Depth-Guided Optimization of Neural Radiance Fields for Indoor Multi-View Stereo (18 citations)
- Interactive NeRF Geometry Editing With Shape Priors (13 citations)
- MILO: Multi-Bounce Inverse Rendering for Indoor Scene With Light-Emitting Objects (13 citations)
- From NeRFLiX to NeRFLiX++: A General NeRF-Agnostic Restorer Paradigm (8 citations)
- Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis (6 citations)
- GiganticNVS: Gigapixel Large-Scale Neural Rendering With Implicit Meta-Deformed Manifold (6 citations)
