AAAI 2024 accepted papers on 3D vision
114 of the 2,864 papers accepted at AAAI 2024 (4.0%) are on 3D vision, compared with 2.4% at AAAI 2023. They fall into 5 topics.
See AAAI 2024 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
3D generation · 35 papers
- Reliable Conflictive Multi-View Learning (126 citations)
- AvatarVerse: High-Quality & Stable 3D Avatar Creation from Text and Pose (45 citations)
- FocalDreamer: Text-Driven 3D Editing via Focal-Fusion Assembly (38 citations)
- Urban Region Embedding via Multi-View Contrastive Prediction (35 citations)
- Mono3DVG: 3D Visual Grounding in Monocular Images (24 citations)
- Aligning Geometric Spatial Layout in Cross-View Geo-Localization via Feature Recombination (23 citations)
- Sparse3D: Distilling Multiview-Consistent Diffusion for Object Reconstruction from Sparse Views (22 citations)
- HybridGait: A Benchmark for Spatial-Temporal Cloth-Changing Gait Recognition with Hybrid Explorations (21 citations)
- H2GFormer: Horizontal-to-Global Voxel Transformer for 3D Semantic Scene Completion (20 citations)
- PVALane: Prior-Guided 3D Lane Detection with View-Agnostic Feature Alignment (19 citations)
- M-BEV: Masked BEV Perception for Robust Autonomous Driving (14 citations)
- RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation (14 citations)
and 23 more in the interactive map.
NeRF and radiance fields · 22 papers
- Aleth-NeRF: Illumination Adaptive NeRF with Concealing Field Assumption (53 citations)
- PNeRFLoc: Visual Localization with Point-Based Neural Radiance Fields (22 citations)
- Sync-NeRF: Generalizing Dynamic NeRFs to Unsynchronized Videos (14 citations)
- CF-NeRF: Camera Parameter Free Neural Radiance Fields with Incremental Learning (13 citations)
- ColNeRF: Collaboration for Generalizable Sparse Input Neural Radiance Field (12 citations)
- Enhancing Neural Radiance Fields with Adaptive Multi-Exposure Fusion: A Bilevel Optimization Approach for Novel View Synthesis (12 citations)
- SpectralNeRF: Physically Based Spectral Rendering with Neural Radiance Field (12 citations)
- Pano-NeRF: Synthesizing High Dynamic Range Novel Views with Geometry from Sparse Low Dynamic Range Panoramic Images (9 citations)
- Colorizing Monochromatic Radiance Fields (8 citations)
- Improving Robustness for Joint Optimization of Camera Pose and Decomposed Low-Rank Tensorial Radiance Fields (7 citations)
- BLiRF: Bandlimited Radiance Fields for Dynamic Scene Modeling (6 citations)
- FPRF: Feed-Forward Photorealistic Style Transfer of Large-Scale 3D Neural Radiance Fields (6 citations)
and 10 more in the interactive map.
Human pose estimation · 21 papers
- SHaRPose: Sparse High-Resolution Representation for Human Pose Estimation (38 citations)
- Disentangled Diffusion-Based 3D Human Pose Estimation with Hierarchical Spatial and Temporal Denoiser (36 citations)
- FusionFormer: A Concise Unified Feature Fusion Transformer for 3D Pose Estimation (21 citations)
- Lifting by Image – Leveraging Image Cues for Accurate 3D Human Pose Estimation (16 citations)
- CatFormer: Category-Level 6D Object Pose Estimation with Transformer (14 citations)
- MFOS: Model-Free & One-Shot Object Pose Estimation (13 citations)
- Deep Semantic Graph Transformer for Multi-View 3D Human Pose Estimation (12 citations)
- A Unified Masked Autoencoder with Patchified Skeletons for Motion Synthesis (10 citations)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (10 citations)
- Expressive Forecasting of 3D Whole-Body Human Motions (7 citations)
- KPA-Tracker: Towards Robust and Real-Time Category-Level Articulated Object 6D Pose Tracking (6 citations)
- Advancing Video Synchronization with Fractional Frame Analysis: Introducing a Novel Dataset and Model (5 citations)
and 9 more in the interactive map.
Face and shape · 19 papers
- NeuSurf: On-Surface Priors for Neural Surface Reconstruction from Sparse Input Views (26 citations)
- NILUT: Conditional Neural Implicit 3D Lookup Tables for Image Enhancement (22 citations)
- Relightable and Animatable Neural Avatars from Videos (18 citations)
- Mimic: Speaking Style Disentanglement for Speech-Driven 3D Facial Animation (17 citations)
- Rethinking Mesh Watermark: Towards Highly Robust and Adaptable Deep 3D Mesh Watermarking (14 citations)
- Learning Dense Correspondence for NeRF-Based Face Reenactment (13 citations)
- Learning Spatially Collaged Fourier Bases for Implicit Neural Representation (10 citations)
- High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field (9 citations)
- NeBLa: Neural Beer-Lambert for 3D Reconstruction of Oral Structures from Panoramic Radiographs (9 citations)
- Fine-Grained Multi-View Hand Reconstruction Using Inverse Rendering (8 citations)
- DLCA-Recon: Dynamic Loose Clothing Avatar Reconstruction from Monocular Videos (6 citations)
- Learning Explicit Contact for Implicit Reconstruction of Hand-Held Objects from Monocular Images (6 citations)
and 7 more in the interactive map.
Depth and stereo · 17 papers
- SQLdepth: Generalizable Self-Supervised Fine-Structured Monocular Depth Estimation (58 citations)
- SD-MVS: Segmentation-Driven Deformation Multi-View Stereo with Spherical Refinement and EM Optimization (28 citations)
- IINet: Implicit Intra-inter Information Fusion for Real-Time Stereo Matching (24 citations)
- BCLNet: Bilateral Consensus Learning for Two-View Correspondence Pruning (20 citations)
- VSFormer: Visual-Spatial Fusion Transformer for Correspondence Pruning (14 citations)
- Joint Demosaicing and Denoising for Spike Camera (13 citations)
- Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo (12 citations)
- PARSAC: Accelerating Robust Multi-Model Fitting with Parallel Sample Consensus (11 citations)
- Evidential Uncertainty-Guided Mitochondria Segmentation for 3D EM Images (9 citations)
- Any-Stereo: Arbitrary Scale Disparity Estimation for Iterative Stereo Matching (7 citations)
- UVAGaze: Unsupervised 1-to-2 Views Adaptation for Gaze Estimation (7 citations)
- Mask-Homo: Pseudo Plane Mask-Guided Unsupervised Multi-Homography Estimation (5 citations)
and 5 more in the interactive map.