IJCV 2021 papers on 3D vision
21 of the 130 papers published in IJCV 2021 (16.2%) are on 3D vision, compared with 16.0% at IJCV 2020. They fall into 5 topics.
See IJCV 2021 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
Human pose estimation · 7 papers
- Multi-level Motion Attention for Human Motion Prediction (99 citations)
- DeMoCap: Low-Cost Marker-Based Motion Capture (49 citations)
- Enhanced 3D Human Pose Estimation from Videos by Using Attention-Based Neural Network with Dilated Convolutions (37 citations)
- View-Invariant, Occlusion-Robust Probabilistic Embedding for Human Pose (22 citations)
- A Shape-Aware Retargeting Approach to Transfer Human Motion and Appearance in Monocular Videos (17 citations)
- Deep Unsupervised 3D Human Body Reconstruction from a Sparse set of Landmarks (11 citations)
- Learning a Robust Part-Aware Monocular 3D Human Pose Estimator via Neural Architecture Search (8 citations)
Depth and stereo · 5 papers
- Computer Vision and Pattern Recognition 2020 (650 citations)
- Unsupervised Scale-Consistent Depth Learning from Video (218 citations)
- Learning to Reconstruct HDR Images from Events, with Applications to Depth and Flow Prediction (73 citations)
- Parallel Single-Pixel Imaging: A General Method for Direct–Global Separation and 3D Shape Reconstruction Under Strong Global Illumination (65 citations)
- Learned Collaborative Stereo Refinement (9 citations)
Face and shape · 5 papers
- 3D-FUTURE: 3D Furniture Shape with TextURE (260 citations)
- Spectral Shape Recovery and Analysis Via Data-driven Connections (21 citations)
- Shape My Face: Registering 3D Face Scans by Surface-to-Surface Translation (20 citations)
- A Numerical Framework for Elastic Surface Matching, Comparison, and Interpolation (19 citations)
- Learning to Caricature via Semantic Shape Transform (15 citations)
3D generation · 3 papers
- Manhattan Room Layout Reconstruction from a Single $$360^{\circ }$$ Image: A Comparative Study of State-of-the-Art Methods (72 citations)
- The Isowarp: The Template-Based Visual Geometry of Isometric Surfaces (14 citations)
- Adding Knowledge to Unsupervised Algorithms for the Recognition of Intent (6 citations)
