IJCV 2022 papers on 3D vision
41 of the 185 papers published in IJCV 2022 (22.2%) are on 3D vision, compared with 16.2% at IJCV 2021. They fall into 4 topics.
See IJCV 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 · 18 papers
- Vis-MVSNet: Visibility-Aware Multi-view Stereo Network (185 citations)
- A CNN Based Approach for the Point-Light Photometric Stereo Problem (42 citations)
- Wide-Angle Image Rectification: A Survey (36 citations)
- Learning Inverse Depth Regression for Pixelwise Visibility-Aware Multi-View Stereo Networks (35 citations)
- Wide-Area Crowd Counting: Multi-view Fusion Networks for Counting in Large Scenes (29 citations)
- Eliminating Temporal Illumination Variations in Whisk-broom Hyperspectral Imaging (24 citations)
- Leveraging Blur Information for Plenoptic Camera Calibration (19 citations)
- 3D Crowd Counting via Geometric Attention-Guided Multi-view Fusion (15 citations)
- Displacement-Invariant Cost Computation for Stereo Matching (14 citations)
- Common Pole–Polar Properties of Central Catadioptric Sphere and Line Images Used for Camera Calibration (8 citations)
- Real-Time Multi-Car Localization and See-Through System (8 citations)
- Spatio-Temporal Outdoor Lighting Aggregation on Image Sequences Using Transformer Networks (8 citations)
and 6 more in the interactive map.
Human pose estimation · 12 papers
- SRT3D: A Sparse Region-Based 3D Object Tracking Approach for the Real World (63 citations)
- Deep Bingham Networks: Dealing with Uncertainty and Ambiguity in Pose Estimation (59 citations)
- Minimal Solvers for Relative Pose Estimation of Multi-Camera Systems using Affine Correspondences (58 citations)
- OpenMonkeyChallenge: Dataset and Benchmark Challenges for Pose Estimation of Non-human Primates (45 citations)
- Consensus-Based Optimization for 3D Human Pose Estimation in Camera Coordinates (34 citations)
- Action2video: Generating Videos of Human 3D Actions (22 citations)
- Animal Pose Tracking: 3D Multimodal Dataset and Token-based Pose Optimization (18 citations)
- Object-Based Visual Camera Pose Estimation From Ellipsoidal Model and 3D-Aware Ellipse Prediction (18 citations)
- Pose Measurement at Small Scale by Spectral Analysis of Periodic Patterns (18 citations)
- Estimating 3D Motion and Forces of Human–Object Interactions from Internet Videos (11 citations)
- Singularity Analysis for the Perspective-Four and Five-Line Problems (9 citations)
- Preface to the Special Issue on Human Pose, Motion, Activities and Shape in 3D (1 citation)
3D generation · 6 papers
- 3D Semantic Scene Completion: A Survey (118 citations)
- Scene Reconstruction with Functional Objects for Robot Autonomy (29 citations)
- Unsupervised Multi-View CNN for Salient View Selection and 3D Interest Point Detection (25 citations)
- RM3D: Robust Data-Efficient 3D Scene Parsing via Traditional and Learnt 3D Descriptors-Based Semantic Region Merging (10 citations)
- 4D Temporally Coherent Multi-Person Semantic Reconstruction and Segmentation (5 citations)
- Instance-Aware Scene Layout Forecasting (1 citation)
Face and shape · 5 papers
- SHARP: Shape-Aware Reconstruction of People in Loose Clothing (23 citations)
- 3DPointCaps++: Learning 3D Representations with Capsule Networks (7 citations)
- Inextensible Surface Reconstruction Under Small Relative Deformations from Distributed Angle Measurements (3 citations)
- ISHIGAKI Retrieval System Using 3D Shape Matching and Combinatorial Optimization (3 citations)
- Shape and Albedo Recovery by Your Phone using Stereoscopic Flash and No-Flash Photography
