IJCV 2020 papers on 3D vision
19 of the 119 papers published in IJCV 2020 (16.0%) are on 3D vision, compared with 27.7% at IJCV 2019. They fall into 4 topics.
See IJCV 2020 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 · 8 papers
- EdgeStereo: An Effective Multi-task Learning Network for Stereo Matching and Edge Detection (205 citations)
- Reference Pose Generation for Long-term Visual Localization via Learned Features and View Synthesis (170 citations)
- A Benchmark and Evaluation of Non-Rigid Structure from Motion (44 citations)
- A Camera Model for Line-Scan Cameras with Telecentric Lenses (32 citations)
- Volume Sweeping: Learning Photoconsistency for Multi-View Shape Reconstruction (14 citations)
- Light Structure from Pin Motion: Geometric Point Light Source Calibration (13 citations)
- Minimal Solvers for Rectifying from Radially-Distorted Scales and Change of Scales (10 citations)
- Necessary and Sufficient Polynomial Constraints on Compatible Triplets of Essential Matrices (4 citations)
Face and shape · 6 papers
- Pix2Vox++: Multi-scale Context-aware 3D Object Reconstruction from Single and Multiple Images (213 citations)
- 3DFaceGAN: Adversarial Nets for 3D Face Representation, Generation, and Translation (64 citations)
- Learning the spatiotemporal variability in longitudinal shape data sets (17 citations)
- Towards Photo-Realistic Facial Expression Manipulation (17 citations)
- Inferring 3D Shapes from Image Collections Using Adversarial Networks (10 citations)
- Pix2Shape: Towards Unsupervised Learning of 3D Scenes from Images Using a View-Based Representation (10 citations)
Human pose estimation · 4 papers
- AdaFuse: Adaptive Multiview Fusion for Accurate Human Pose Estimation in the Wild (123 citations)
- Learning Multi-human Optical Flow (36 citations)
- View Transfer on Human Skeleton Pose: Automatically Disentangle the View-Variant and View-Invariant Information for Pose Representation Learning (28 citations)
- DGPose: Deep Generative Models for Human Body Analysis (14 citations)
Gaussian splatting · 1 paper
- Temporally Coherent General Dynamic Scene Reconstruction (14 citations)
