TPAMI 2022 papers on 3D vision
55 of the 583 papers published in TPAMI 2022 (9.4%) are on 3D vision, compared with 13.6% at TPAMI 2021. They fall into 5 topics.
See TPAMI 2022 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 · 20 papers
- Rank-One Prior: Real-Time Scene Recovery (171 citations)
- Multi-Scale Geometric Consistency Guided and Planar Prior Assisted Multi-View Stereo (102 citations)
- Deep Depth Completion from Extremely Sparse Data: A Survey (88 citations)
- Towards Accurate Reconstruction of 3D Scene Shape From A Single Monocular Image (66 citations)
- Accurate 3-DoF Camera Geo-Localization via Ground-to-Satellite Image Matching (60 citations)
- Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging (58 citations)
- Content-Aware Unsupervised Deep Homography Estimation and Its Extensions (45 citations)
- BiFuse++: Self-Supervised and Efficient Bi-Projection Fusion for $360^{\circ }$ Depth Estimation (43 citations)
- Vid2CAD: CAD Model Alignment Using Multi-View Constraints From Videos (43 citations)
- EM-Driven Unsupervised Learning for Efficient Motion Segmentation (37 citations)
- Ultra-High Temporal Resolution Visual Reconstruction From a Fovea-Like Spike Camera via Spiking Neuron Model (31 citations)
- Unsupervised Global and Local Homography Estimation With Motion Basis Learning (27 citations)
and 8 more in the interactive map.
Human pose estimation · 16 papers
- AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-Time (855 citations)
- Simultaneously-Collected Multimodal Lying Pose Dataset: Enabling In-Bed Human Pose Monitoring (104 citations)
- Adaptive Multi-View and Temporal Fusing Transformer for 3D Human Pose Estimation (99 citations)
- VoxelTrack: Multi-Person 3D Human Pose Estimation and Tracking in the Wild (99 citations)
- Investigating Pose Representations and Motion Contexts Modeling for 3D Motion Prediction (94 citations)
- ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild (54 citations)
- Towards High Performance Low Complexity Calibration in Appearance Based Gaze Estimation (46 citations)
- BodyPressure - Inferring Body Pose and Contact Pressure From a Depth Image (41 citations)
- From Human Pose Similarity Metric to 3D Human Pose Estimator: Temporal Propagating LSTM Networks (37 citations)
- Recurrent 3D Hand Pose Estimation Using Cascaded Pose-Guided 3D Alignments (33 citations)
- Dual Networks Based 3D Multi-Person Pose Estimation From Monocular Video (31 citations)
- Object-Occluded Human Shape and Pose Estimation With Probabilistic Latent Consistency (27 citations)
and 4 more in the interactive map.
Face and shape · 13 papers
- FSGANv2: Improved Subject Agnostic Face Swapping and Reenactment (82 citations)
- DeepCloth: Neural Garment Representation for Shape and Style Editing (74 citations)
- MPS-NeRF: Generalizable 3D Human Rendering From Multiview Images (59 citations)
- Learning to Detect 3D Symmetry From Single-View RGB-D Images With Weak Supervision (51 citations)
- Pixel2Mesh++: 3D Mesh Generation and Refinement From Multi-View Images (48 citations)
- Learning View-Based Graph Convolutional Network for Multi-View 3D Shape Analysis (43 citations)
- Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation (39 citations)
- ResNet-LDDMM: Advancing the LDDMM Framework using Deep Residual Networks (39 citations)
- Beyond 3DMM: Learning to Capture High-Fidelity 3D Face Shape (20 citations)
- 4D Atlas: Statistical Analysis of the Spatiotemporal Variability in Longitudinal 3D Shape Data (13 citations)
- Self-supervised 3D Representation Learning of Dressed Humans from Social Media Videos (12 citations)
- Towards Lightweight Pixel-Wise Hallucination for Heterogeneous Face Recognition (8 citations)
and 1 more in the interactive map.
3D generation · 4 papers
- KITTI-360: A Novel Dataset and Benchmarks for Urban Scene Understanding in 2D and 3D (898 citations)
- Geometry-Guided Street-View Panorama Synthesis From Satellite Imagery (55 citations)
- RobustFusion: Robust Volumetric Performance Reconstruction Under Human-Object Interactions From Monocular RGBD Stream (29 citations)
- Voxel-Mesh Network for Geodesic-Aware 3D Semantic Segmentation of Indoor Scenes (16 citations)
