IJCV 2018 papers on 3D vision
26 of the 78 papers published in IJCV 2018 (33.3%) are on 3D vision, compared with 31.1% at IJCV 2017. They fall into 4 topics.
See IJCV 2018 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
- The Menpo Benchmark for Multi-pose 2D and 3D Facial Landmark Localisation and Tracking (100 citations)
- Cluster Sparsity Field: An Internal Hyperspectral Imagery Prior for Reconstruction (84 citations)
- Occlusion-Aware 3D Morphable Models and an Illumination Prior for Face Image Analysis (77 citations)
- Deep Appearance Models: A Deep Boltzmann Machine Approach for Face Modeling (32 citations)
- Motion Deblurring of Faces (31 citations)
- 3D Interpreter Networks for Viewer-Centered Wireframe Modeling (24 citations)
- Scale-Free Registrations in 3D: 7 Degrees of Freedom with Fourier Mellin SOFT Transforms (21 citations)
- Learning to Predict 3D Surfaces of Sculptures from Single and Multiple Views (14 citations)
- An Approximate Shading Model with Detail Decomposition for Object Relighting (12 citations)
- Elastic Alignment of Triangular Surface Meshes (1 citation)
Human pose estimation · 8 papers
- Image-Based Synthesis for Deep 3D Human Pose Estimation (246 citations)
- Depth-Based Hand Pose Estimation: Methods, Data, and Challenges (103 citations)
- Fusing Visual and Inertial Sensors with Semantics for 3D Human Pose Estimation (81 citations)
- Learning Latent Representations of 3D Human Pose with Deep Neural Networks (75 citations)
- Describing Upper-Body Motions Based on Labanotation for Learning-from-Observation Robots (33 citations)
- Equivalent Constraints for Two-View Geometry: Pose Solution/Pure Rotation Identification and 3D Reconstruction (27 citations)
- Joint Contour Filtering (10 citations)
- Synthesizing a Scene-Specific Pedestrian Detector and Pose Estimator for Static Video Surveillance
Depth and stereo · 4 papers
- What Makes Good Synthetic Training Data for Learning Disparity and Optical Flow Estimation? (193 citations)
- Combining Shape from Shading and Stereo: A Joint Variational Method for Estimating Depth, Illumination and Albedo (33 citations)
- Superpixel-Guided Two-View Deterministic Geometric Model Fitting (18 citations)
- A Differential Approach to Shape from Polarisation: A Level-Set Characterisation (15 citations)
3D generation · 4 papers
- Sim4CV: A Photo-Realistic Simulator for Computer Vision Applications (193 citations)
- Configurable 3D Scene Synthesis and 2D Image Rendering with Per-pixel Ground Truth Using Stochastic Grammars (82 citations)
- Complete 3D Scene Parsing from an RGBD Image (32 citations)
- Virtual Training for a Real Application: Accurate Object-Robot Relative Localization Without Calibration (24 citations)
