TPAMI 2021 papers on 3D vision
70 of the 516 papers published in TPAMI 2021 (13.6%) are on 3D vision, compared with 17.9% at TPAMI 2020. They fall into 5 topics.
See TPAMI 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
Depth and stereo · 26 papers
- Visual Camera Re-Localization from RGB and RGB-D Images Using DSAC (237 citations)
- On the Synergies between Machine Learning and Binocular Stereo for Depth Estimation from Images: a Survey (169 citations)
- Auto-Rectify Network for Unsupervised Indoor Depth Estimation (103 citations)
- Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction (82 citations)
- A Novel Occlusion-aware Vote Cost for Light Field Depth Estimation (74 citations)
- Revisiting Light Field Rendering with Deep Anti-Aliasing Neural Network (68 citations)
- On the confidence of stereo matching in a deep-learning era: a quantitative evaluation (56 citations)
- High Resolution, Deep Imaging Using Confocal Time-of-Flight Diffuse Optical Tomography (48 citations)
- A Pose-Only Solution to Visual Reconstruction and Navigation (45 citations)
- Learning Optimal Wavefront Shaping for Multi-Channel Imaging (44 citations)
- Robust Event-Based Vision Model Estimation by Dispersion Minimisation (36 citations)
- Multiple Human Association and Tracking from Egocentric and Complementary Top Views (35 citations)
and 14 more in the interactive map.
Face and shape · 22 papers
- PaMIR: Parametric Model-Conditioned Implicit Representation for Image-Based Human Reconstruction (336 citations)
- AvatarMe++: Facial Shape and BRDF Inference With Photorealistic Rendering-Aware GANs (71 citations)
- Fast-GANFIT: Generative Adversarial Network for High Fidelity 3D Face Reconstruction (69 citations)
- SkeletonNet: A Topology-Preserving Solution for Learning Mesh Reconstruction of Object Surfaces From RGB Images (44 citations)
- Face Restoration via Plug-and-Play 3D Facial Priors (40 citations)
- A Sparse and Locally Coherent Morphable Face Model for Dense Semantic Correspondence Across Heterogeneous 3D Faces (28 citations)
- Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos (27 citations)
- Detailed Avatar Recovery From Single Image (23 citations)
- View-Aware Geometry-Structure Joint Learning for Single-View 3D Shape Reconstruction (23 citations)
- HUMBI: A Large Multiview Dataset of Human Body Expressions and Benchmark Challenge (21 citations)
- GigaMVS: A Benchmark for Ultra-Large-Scale Gigapixel-Level 3D Reconstruction (20 citations)
- Survey and Evaluation of Neural 3D Shape Classification Approaches (15 citations)
and 10 more in the interactive map.
Human pose estimation · 16 papers
- Spatiotemporal Co-Attention Recurrent Neural Networks for Human-Skeleton Motion Prediction (291 citations)
- Fast and Robust Multi-Person 3D Pose Estimation and Tracking From Multiple Views (119 citations)
- VPN++: Rethinking Video-Pose Embeddings for Understanding Activities of Daily Living (98 citations)
- Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation (72 citations)
- DPODv2: Dense Correspondence-Based 6 DoF Pose Estimation (60 citations)
- Heatmap Regression via Randomized Rounding (52 citations)
- Monocular 3D Pose Estimation via Pose Grammar and Data Augmentation (51 citations)
- Liquid Warping GAN With Attention: A Unified Framework for Human Image Synthesis (49 citations)
- UniPose+: A Unified Framework for 2D and 3D Human Pose Estimation in Images and Videos (41 citations)
- HandVoxNet++: 3D Hand Shape and Pose Estimation Using Voxel-Based Neural Networks (38 citations)
- HEMlets PoSh: Learning Part-Centric Heatmap Triplets for 3D Human Pose and Shape Estimation (36 citations)
- 3D Human Pose, Shape and Texture from Low-Resolution Images and Videos (34 citations)
and 4 more in the interactive map.
3D generation · 4 papers
- XSleepNet: Multi-View Sequential Model for Automatic Sleep Staging (306 citations)
- A Fully Automated Method for 3D Individual Tooth Identification and Segmentation in Dental CBCT (182 citations)
- JRDB: A Dataset and Benchmark of Egocentric Robot Visual Perception of Humans in Built Environments (171 citations)
- Anisotropic Convolutional Neural Networks for RGB-D based Semantic Scene Completion (18 citations)
