AAAI 2022 accepted papers on 3D vision
35 of the 1,319 papers accepted at AAAI 2022 (2.7%) are on 3D vision, compared with 1.9% at AAAI 2021. They fall into 5 topics.
See AAAI 2022 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
Human pose estimation · 11 papers
- Pose-Guided Feature Disentangling for Occluded Person Re-identification Based on Transformer (231 citations)
- Learning to Predict 3D Lane Shape and Camera Pose from a Single Image via Geometry Constraints (51 citations)
- Efficient Virtual View Selection for 3D Hand Pose Estimation (42 citations)
- Self-Supervised Category-Level 6D Object Pose Estimation with Deep Implicit Shape Representation (39 citations)
- AdaptivePose: Human Parts as Adaptive Points (25 citations)
- MoCaNet: Motion Retargeting In-the-Wild via Canonicalization Networks (16 citations)
- Geometry-Contrastive Transformer for Generalized 3D Pose Transfer (13 citations)
- Adaptive Hypergraph Neural Network for Multi-Person Pose Estimation (12 citations)
- REMOTE: Reinforced Motion Transformation Network for Semi-supervised 2D Pose Estimation in Videos (10 citations)
- P^3-Net: Part Mobility Parsing from Point Cloud Sequences via Learning Explicit Point Correspondence (5 citations)
- Neural Marionette: Unsupervised Learning of Motion Skeleton and Latent Dynamics from Volumetric Video (4 citations)
Face and shape · 10 papers
- Deep Implicit Statistical Shape Models for 3D Medical Image Delineation (33 citations)
- MOST-GAN: 3D Morphable StyleGAN for Disentangled Face Image Manipulation (33 citations)
- Detailed Facial Geometry Recovery from Multi-View Images by Learning an Implicit Function (22 citations)
- Texture Reformer: Towards Fast and Universal Interactive Texture Transfer (14 citations)
- Local Surface Descriptor for Geometry and Feature Preserved Mesh Denoising (11 citations)
- Pose Adaptive Dual Mixup for Few-Shot Single-View 3D Reconstruction (9 citations)
- Towards Accurate Facial Motion Retargeting with Identity-Consistent and Expression-Exclusive Constraints (8 citations)
- Towards High-Fidelity Face Self-Occlusion Recovery via Multi-View Residual-Based GAN Inversion (8 citations)
- Cross-Species 3D Face Morphing via Alignment-Aware Controller (7 citations)
- Joint Deep Multi-Graph Matching and 3D Geometry Learning from Inhomogeneous 2D Image Collections (6 citations)
Depth and stereo · 9 papers
- Trusted Multi-View Deep Learning with Opinion Aggregation (79 citations)
- ACDNet: Adaptively Combined Dilated Convolution for Monocular Panorama Depth Estimation (61 citations)
- Improving 360 Monocular Depth Estimation via Non-local Dense Prediction Transformer and Joint Supervised and Self-Supervised Learning (30 citations)
- Transfer Learning for Color Constancy via Statistic Perspective (21 citations)
- Rendering-Aware HDR Environment Map Prediction from a Single Image (19 citations)
- FisheyeHDK: Hyperbolic Deformable Kernel Learning for Ultra-Wide Field-of-View Image Recognition (16 citations)
- Monocular Camera-Based Point-Goal Navigation by Learning Depth Channel and Cross-Modality Pyramid Fusion (10 citations)
- Anisotropic Fourier Features for Neural Image-Based Rendering and Relighting (7 citations)
- MMA: Multi-Camera Based Global Motion Averaging (5 citations)
3D generation · 4 papers
- DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer (130 citations)
- FFNet: Frequency Fusion Network for Semantic Scene Completion (27 citations)
- Pose Guided Image Generation from Misaligned Sources via Residual Flow Based Correction (5 citations)
- Texture Generation Using Dual-Domain Feature Flow with Multi-View Hallucinations (2 citations)
