AAAI 2026 accepted papers on 3D vision
246 of the 4,417 papers accepted at AAAI 2026 (5.6%) are on 3D vision, compared with 4.0% at AAAI 2025. They fall into 6 topics.
See AAAI 2026 in the interactive map
Working on something in this area? Describe your idea in scime atlas to see the closest accepted papers by meaning and how crowded the spot has become.
Topics and papers
Gaussian splatting · 79 papers
- PCGS: Progressive Compression of 3D Gaussian Splatting (9 citations)
- SkySplat: Generalizable 3D Gaussian Splatting from Multi-Temporal Sparse Satellite Images (9 citations)
- D-FCGS: Feedforward Compression of Dynamic Gaussian Splatting for Free-Viewpoint Videos (4 citations)
- GAGS: Granularity-Aware Feature Distillation for Language Gaussian Splatting (4 citations)
- NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representations (4 citations)
- Rethinking Rainy 3D Scene Reconstruction via Perspective Transforming and Brightness Tuning (4 citations)
- WeatherEdit: Controllable Weather Editing with 4D Gaussian Field (4 citations)
- Arbitrary-Scale 3D Gaussian Super-Resolution (3 citations)
- Deblur4DGS: 4D Gaussian Splatting from Blurry Monocular Video (3 citations)
- MoBGS: Motion Deblurring Dynamic 3D Gaussian Splatting for Blurry Monocular Video (3 citations)
- Perceptual Quality Assessment of 3D Gaussian Splatting: A Subjective Dataset and Prediction Metric (3 citations)
- Sparse4DGS: 4D Gaussian Splatting for Sparse-Frame Dynamic Scene Reconstruction (3 citations)
and 67 more in the interactive map.
3D generation · 69 papers
- DeOcc-1-to-3: 3D De-Occlusion from a Single Image via Self-Supervised Multi-View Diffusion (4 citations)
- Automatic Translational Correction of Multi-View Coronary Angiography Based on Auto-Annotation Data Generation (2 citations)
- EAGLE: Episodic Appearance- and Geometry-aware Memory for Unified 2D-3D Visual Query Localization in Egocentric Vision (2 citations)
- Open-World 3D Scene Graph Generation for Retrieval-Augmented Reasoning (2 citations)
- Towards Affordance-Aware Robotic Dexterous Grasping with Human-like Priors (2 citations)
- Understanding Dynamic Scenes in Ego Centric 4D Point Clouds (2 citations)
- Whole-Body Coordination for Dynamic Object Grasping with Legged Manipulators (2 citations)
- WorldGrow: Generating Infinite 3D World (2 citations)
- AlignCVC: Aligning Cross-View Consistency for Single-Image-to-3D Generation (1 citation)
- CyC3D: Fine-grained Controllable 3D Generation via Cycle Consistency Regularization (1 citation)
- DiffNR: Diffusion-Enhanced Neural Representation Optimization for Sparse-View 3D Tomographic Reconstruction (1 citation)
- FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation (1 citation)
and 57 more in the interactive map.
Face and shape · 33 papers
- HumanPro: Single-view 3D Clothed Human Reconstruction with Progressive Normal Guidance (5 citations)
- BridgeShape: Latent Diffusion Schrödinger Bridge for 3D Shape Completion (1 citation)
- DcMatch: Unsupervised Multi-Shape Matching with Dual-Level Consistency (1 citation)
- I-INR: Iterative Implicit Neural Representations (1 citation)
- Implicit Neural Representation with Multi-Scale Sine Activation (1 citation)
- Learning Compact Latent Space for Representing Neural Signed Distance Functions with High-fidelity Geometry Details (1 citation)
- MDND: Unsupervised Learning Guided by Non-Differentiable Refinement for Shape Correspondence (1 citation)
- PFAvatar: Pose-Fusion 3D Personalized Avatar Reconstruction from Real-World Outfit-of-the-Day Photos (1 citation)
- Single-Stage fMRI-to-3D Reconstruction via Viewpoint-Aware Embedding and Hierarchical Guidance (1 citation)
- Unsupervised Contrastive Learning for Efficient and Robust Spectral Shape Matching (1 citation)
- Unsupervised Multi-Parameter Inverse Solving for Reducing Ring Artifacts in 3D X-Ray CBCT (1 citation)
- Anti-Avatar: Protect Against Unauthorized 3D Head Avatar Generation via Dual-Space Divergence
and 21 more in the interactive map.
Human pose estimation · 33 papers
- End-to-End Multi-Person Pose Estimation with Pose-Aware Video Transformer (3 citations)
- Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds (2 citations)
- RacketVision: A Multiple Racket Sports Benchmark for Unified Ball and Racket Analysis (2 citations)
- Breaking the Passive Learning Trap: An Active Perception Strategy for Human Motion Prediction (1 citation)
- CoordAR: One-Reference 6D Pose Estimation of Novel Objects via Autoregressive Coordinate Map Generation (1 citation)
- HandMCM: Multi-modal Point Cloud-based Correspondence State Space Model for 3D Hand Pose Estimation (1 citation)
- Hi-EF: Benchmarking Emotion Forecasting in Human-interaction (1 citation)
- Improving Sparse IMU-based Motion Capture with Motion Label Smoothing (1 citation)
- Robust Long-Term Test-Time Adaptation for 3D Human Pose Estimation Through Motion Discretization (1 citation)
- SAME: Spatial-Aware Multimodal Egocentric Human Pose Estimation (1 citation)
- VPHO: Joint Visual-Physical Cue Learning and Aggregation for Hand-Object Pose Estimation (1 citation)
- Attentive Keypoint Identification: Progressive Spatiotemporal Refinement for Video-based Human Pose Estimation
and 21 more in the interactive map.
Depth and stereo · 29 papers
- Phys-Liquid: A Physics-Informed Dataset for Estimating 3D Geometry and Volume of Transparent Deformable Liquids (2 citations)
- A Study of Finetuning Video Transformers for Multi-view Geometry Tasks (1 citation)
- Collaborative Feature Matching with Progressive Correspondence Learning (1 citation)
- Depth-Synergized Mamba Meets Memory Experts for All-Day Image Reflection Separation (1 citation)
- EC-MVSNet: Enhanced Cascaded Multi-View Stereo with Cross-Scale Relevance Integration (1 citation)
- Ev-iCRF: Self-supervised Event-guided iCRF Estimation for HDR Image Reconstruction (1 citation)
- MRGeo: Robust Cross-View Geo-Localization of Corrupted Images via Spatial and Channel Feature Enhancement (1 citation)
- RAW-Flow: Advancing RGB-to-RAW Image Reconstruction with Deterministic Latent Flow Matching (1 citation)
- RflyPano: A Panoramic Benchmark for Ultra-low Altitude UAV Localization Powered by RflySim (1 citation)
- RiemanLine: Riemannian Manifold Representation of 3D Lines for Factor Graph Optimization (1 citation)
- A Paradigm Shift in High-Resolution Depth Estimation Using SPAD-Based LiDAR Histograms: From Signal Filtering to Lightweight Similarity Learning
- AdaDepth: Exploiting Inherent Scene Information for Self-Supervised Depth Estimation in Dynamic Scenes
and 17 more in the interactive map.