IJCV 2023 papers on 3D vision
40 of the 220 papers published in IJCV 2023 (18.2%) are on 3D vision, compared with 22.2% at IJCV 2022. They fall into 5 topics.
See IJCV 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
Face and shape · 13 papers
- DOVE: Learning Deformable 3D Objects by Watching Videos (53 citations)
- Elastic Shape Analysis of Surfaces with Second-Order Sobolev Metrics: A Comprehensive Numerical Framework (41 citations)
- Disentangling Geometric Deformation Spaces in Generative Latent Shape Models (11 citations)
- Building 3D Generative Models from Minimal Data (10 citations)
- Skeleton Ground Truth Extraction: Methodology, Annotation Tool and Benchmarks (9 citations)
- Towards Fine-Grained Optimal 3D Face Dense Registration: An Iterative Dividing and Diffusing Method (9 citations)
- Free-view Face Relighting Using a Hybrid Parametric Neural Model on a SMALL-OLAT Dataset (8 citations)
- BARC: Breed-Augmented Regression Using Classification for 3D Dog Reconstruction from Images (7 citations)
- Expression-Preserving Face Frontalization Improves Visually Assisted Speech Processing (7 citations)
- PartCom: Part Composition Learning for 3D Open-Set Recognition (7 citations)
- A Deeper Analysis of Volumetric Relightable Faces (4 citations)
- Virtual Restoration of Ancient Wooden Ships Through Non-rigid 3D Shape Assembly with Ruled-Surface FFD (3 citations)
and 1 more in the interactive map.
Depth and stereo · 10 papers
- Deep Unfolding for Snapshot Compressive Imaging (113 citations)
- Coatrsnet: Fully Exploiting Convolution and Attention for Stereo Matching by Region Separation (27 citations)
- Through Hawks’ Eyes: Synthetically Reconstructing the Visual Field of a Bird in Flight (24 citations)
- Deep Depth from Focal Stack with Defocus Model for Camera-Setting Invariance (23 citations)
- Indoor Obstacle Discovery on Reflective Ground via Monocular Camera (13 citations)
- Relating View Directions of Complementary-View Mobile Cameras via the Human Shadow (10 citations)
- Single Pixel Spectral Color Constancy (10 citations)
- A Minimal Solution for Image-Based Sphere Estimation (9 citations)
- Towards a Unified Network for Robust Monocular Depth Estimation: Network Architecture, Training Strategy and Dataset (7 citations)
- View Birdification in the Crowd: Ground-Plane Localization from Perceived Movements (5 citations)
Human pose estimation · 10 papers
- Learning Enriched Hop-Aware Correlation for Robust 3D Human Pose Estimation (32 citations)
- Efficient Annotation and Learning for 3D Hand Pose Estimation: A Survey (27 citations)
- Cascaded Iterative Transformer for Jointly Predicting Facial Landmark, Occlusion Probability and Head Pose (24 citations)
- Improved 3D Markerless Mouse Pose Estimation Using Temporal Semi-supervision (22 citations)
- Lifting 2D Human Pose to 3D with Domain Adapted 3D Body Concept (19 citations)
- Dual Graph Networks for Pose Estimation in Crowded Scenes (14 citations)
- On Making SIFT Features Affine Covariant (14 citations)
- SyDog-Video: A Synthetic Dog Video Dataset for Temporal Pose Estimation (10 citations)
- Perspective-1-Ellipsoid: Formulation, Analysis and Solutions of the Camera Pose Estimation Problem from One Ellipse-Ellipsoid Correspondence (9 citations)
- Refractive Pose Refinement
3D generation · 5 papers
- Automatic Generation of 3D Scene Animation Based on Dynamic Knowledge Graphs and Contextual Encoding (25 citations)
- Multi-view Consistent Generative Adversarial Networks for Compositional 3D-Aware Image Synthesis (24 citations)
- Single-View View Synthesis with Self-rectified Pseudo-Stereo (8 citations)
- InstaBoost++: Visual Coherence Principles for Unified 2D/3D Instance Level Data Augmentation (6 citations)
- Performing Melanoma Diagnosis by an Effective Multi-view Convolutional Network Architecture (2 citations)
