TPAMI 2019 papers on 3D vision
47 of the 304 papers published in TPAMI 2019 (15.5%) are on 3D vision, compared with 17.3% at TPAMI 2018. They fall into 4 topics.
See TPAMI 2019 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 · 21 papers
- Learning Depth with Convolutional Spatial Propagation Network (358 citations)
- Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding (316 citations)
- Confidence Propagation through CNNs for Guided Sparse Depth Regression (296 citations)
- Stereo Matching Using Multi-Level Cost Volume and Multi-Scale Feature Constancy (125 citations)
- SurfelMeshing: Online Surfel-Based Mesh Reconstruction (96 citations)
- Intel® RealSense™ SR300 Coded Light Depth Camera (85 citations)
- Unsupervised Deep Visual-Inertial Odometry with Online Error Correction for RGB-D Imagery (85 citations)
- Semi-Supervised Adversarial Monocular Depth Estimation (61 citations)
- Superpixel Soup: Monocular Dense 3D Reconstruction of a Complex Dynamic Scene (42 citations)
- Snapshot Compressive ToF+Spectral Imaging via Optimized Color-Coded Apertures (38 citations)
- Progressive Fusion for Unsupervised Binocular Depth Estimation Using Cycled Networks (30 citations)
- Complex-Valued Disparity: Unified Depth Model of Depth from Stereo, Depth from Focus, and Depth from Defocus Based on the Light Field Gradient (24 citations)
and 9 more in the interactive map.
Human pose estimation · 17 papers
- OpenPose: Realtime Multi-Person 2D Pose Estimation Using Part Affinity Fields (6,288 citations)
- LCR-Net++: Multi-person 2D and 3D Pose Detection in Natural Images (297 citations)
- Feature Boosting Network For 3D Pose Estimation (135 citations)
- 3D Human Pose Machines with Self-supervised Learning (105 citations)
- Pose-Guided Representation Learning for Person Re-Identification (104 citations)
- Generalized Feedback Loop for Joint Hand-Object Pose Estimation (82 citations)
- Towards Efficient U-Nets: A Coupled and Quantized Approach (63 citations)
- Contactless Biometric Identification Using 3D Finger Knuckle Patterns (52 citations)
- RotationNet for Joint Object Categorization and Unsupervised Pose Estimation from Multi-View Images (50 citations)
- Forecasting People Trajectories and Head Poses by Jointly Reasoning on Tracklets and Vislets (49 citations)
- Adversarial Learning of Structure-Aware Fully Convolutional Networks for Landmark Localization (48 citations)
- Rolling Shutter Camera Absolute Pose (30 citations)
and 5 more in the interactive map.
Face and shape · 7 papers
- Image-Based 3D Object Reconstruction: State-of-the-Art and Trends in the Deep Learning Era (465 citations)
- On Learning 3D Face Morphable Model from In-the-Wild Images (143 citations)
- 3D Fingerprint Recognition based on Ridge-Valley-Guided 3D Reconstruction and 3D Topology Polymer Feature Extraction (45 citations)
- Weakly-Supervised Learning of Category-Specific 3D Object Shapes (31 citations)
- Local Deformable 3D Reconstruction with Cartan's Connections (23 citations)
- Hierarchical Surface Prediction (18 citations)
- Hierarchical Bayesian Inverse Lighting of Portraits with a Virtual Light Stage (2 citations)
