IJCV 2024 papers on 3D vision
36 of the 343 papers published in IJCV 2024 (10.5%) are on 3D vision, compared with 18.2% at IJCV 2023. They fall into 6 topics.
See IJCV 2024 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 · 10 papers
- Neural Vector Fields for Implicit Surface Representation and Inference (14 citations)
- Face3DAdv: Exploiting Robust Adversarial 3D Patches on Physical Face Recognition (12 citations)
- MoDA: Modeling Deformable 3D Objects from Casual Videos (11 citations)
- DisCO: Portrait Distortion Correction with Perspective-Aware 3D GANs (9 citations)
- Continuous Spatial-Spectral Reconstruction via Implicit Neural Representation (7 citations)
- Draw Sketch, Draw Flesh: Whole-Body Computed Tomography from Any X-Ray Views (6 citations)
- Pseudo-Plane Regularized Signed Distance Field for Neural Indoor Scene Reconstruction (5 citations)
- Improving 3D Finger Traits Recognition via Generalizable Neural Rendering (4 citations)
- Basis Restricted Elastic Shape Analysis on the Space of Unregistered Surfaces (3 citations)
- Polynomial Implicit Neural Framework for Promoting Shape Awareness in Generative Models (1 citation)
Depth and stereo · 8 papers
- HSCNet++: Hierarchical Scene Coordinate Classification and Regression for Visual Localization with Transformer (48 citations)
- IEBins: Iterative Elastic Bins for Monocular Depth Estimation and Completion (28 citations)
- GyroFlow+: Gyroscope-Guided Unsupervised Deep Homography and Optical Flow Learning (21 citations)
- Towards Robust Monocular Depth Estimation: A New Baseline and Benchmark (20 citations)
- A Geometric Model for Polarization Imaging on Projective Cameras (6 citations)
- A Survey on Adaptive Cameras (6 citations)
- PL$${}_{1}$$P: Point-Line Minimal Problems under Partial Visibility in Three Views (6 citations)
- Are Multi-view Edges Incomplete for Depth Estimation? (2 citations)
3D generation · 8 papers
- 2D Semantic-Guided Semantic Scene Completion (19 citations)
- 4Seasons: Benchmarking Visual SLAM and Long-Term Localization for Autonomous Driving in Challenging Conditions (17 citations)
- Hyper-3DG: Text-to-3D Gaussian Generation via Hypergraph (17 citations)
- MVTN: Learning Multi-view Transformations for 3D Understanding (17 citations)
- Beyond Talking – Generating Holistic 3D Human Dyadic Motion for Communication (16 citations)
- Structured Generative Models for Scene Understanding (11 citations)
- ToTem NRSfM: Object-Wise Non-rigid Structure-from-Motion with a Topological Template (7 citations)
- SLIDE: A Unified Mesh and Texture Generation Framework with Enhanced Geometric Control and Multi-view Consistency (2 citations)
Human pose estimation · 7 papers
- A Survey on Global LiDAR Localization: Challenges, Advances and Open Problems (160 citations)
- 3D-MuPPET: 3D Multi-Pigeon Pose Estimation and Tracking (34 citations)
- InterCap: Joint Markerless 3D Tracking of Humans and Objects in Interaction from Multi-view RGB-D Images (28 citations)
- Accurate and Efficient Object Pose Estimation via the Aggregation of Diffusion Features (21 citations)
- Event-Based Non-rigid Reconstruction of Low-Rank Parametrized Deformations from Contours (15 citations)
- Object Pose Estimation Based on Multi-precision Vectors and Seg-Driven PnP (6 citations)
- Editor’s Note: Special Issue on German Conference on Pattern Recognition (DAGM GCPR)
