AAAI 2021 accepted papers on 3D vision
31 of the 1,654 papers accepted at AAAI 2021 (1.9%) are on 3D vision, compared with 2.3% at AAAI 2020. They fall into 4 topics.
See AAAI 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
Human pose estimation · 11 papers
- Aggregated Multi-GANs for Controlled 3D Human Motion Prediction (57 citations)
- Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular Videos (43 citations)
- Exploiting Learnable Joint Groups for Hand Pose Estimation (37 citations)
- Learning Complex 3D Human Self-Contact (33 citations)
- PC-HMR: Pose Calibration for 3D Human Mesh Recovery from 2D Images/Videos (27 citations)
- Gene Regulatory Network Inference using 3D Convolutional Neural Network (25 citations)
- Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation (17 citations)
- Deductive Learning for Weakly-Supervised 3D Human Pose Estimation via Uncalibrated Cameras (15 citations)
- RSGNet: Relation based Skeleton Graph Network for Crowded Scenes Pose Estimation (15 citations)
- SIMPLE: SIngle-network with Mimicking and Point Learning for Bottom-up Human Pose Estimation (14 citations)
- LCollision: Fast Generation of Collision-Free Human Poses using Learned Non-Penetration Constraints (5 citations)
Depth and stereo · 8 papers
- FCFR-Net: Feature Fusion based Coarse-to-Fine Residual Learning for Depth Completion (117 citations)
- IDOL: Inertial Deep Orientation-Estimation and Localization (115 citations)
- Attention-based Multi-Level Fusion Network for Light Field Depth Estimation (93 citations)
- Patch-Wise Attention Network for Monocular Depth Estimation (67 citations)
- EMLight: Lighting Estimation via Spherical Distribution Approximation (54 citations)
- Deep Event Stereo Leveraged by Event-to-Image Translation (31 citations)
- Optical Flow Estimation from a Single Motion-blurred Image (19 citations)
- A Global Occlusion-Aware Approach to Self-Supervised Monocular Visual Odometry (5 citations)
Face and shape · 6 papers
- Automated Model Design and Benchmarking of Deep Learning Models for COVID-19 Detection with Chest CT Scans (45 citations)
- MeInGame: Create a Game Character Face from a Single Portrait (33 citations)
- Oral-3D: Reconstructing the 3D Structure of Oral Cavity from Panoramic X-ray (28 citations)
- Learning Local Neighboring Structure for Robust 3D Shape Representation (17 citations)
- Learning Flexibly Distributional Representation for Low-quality 3D Face Recognition (13 citations)
- Shape-Pose Ambiguity in Learning 3D Reconstruction from Images (2 citations)
3D generation · 6 papers
- Semantic MapNet: Building Allocentric Semantic Maps and Representations from Egocentric Views (60 citations)
- SPIN: Structure-Preserving Inner Offset Network for Scene Text Recognition (34 citations)
- XraySyn: Realistic View Synthesis From a Single Radiograph Through CT Priors (17 citations)
- Very Important Person Localization in Unconstrained Conditions: A New Benchmark (13 citations)
- Holistic Multi-View Building Analysis in the Wild with Projection Pooling (4 citations)
- In-game Residential Home Planning via Visual Context-aware Global Relation Learning (4 citations)
