CVPR 2024 accepted papers on Point clouds
102 of the 2,716 papers accepted at CVPR 2024 (3.8%) are on Point clouds, compared with 5.1% at CVPR 2023. They fall into 4 topics.
See CVPR 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
Point cloud classification · 56 papers
- Point Transformer V3: Simpler Faster Stronger (600 citations)
- LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding Reasoning and Planning (84 citations)
- RCooper: A Real-world Large-scale Dataset for Roadside Cooperative Perception (58 citations)
- Open3DSG: Open-Vocabulary 3D Scene Graphs from Point Clouds with Queryable Objects and Open-Set Relationships (54 citations)
- SparseOcc: Rethinking Sparse Latent Representation for Vision-Based Semantic Occupancy Prediction (53 citations)
- Towards Large-scale 3D Representation Learning with Multi-dataset Point Prompt Training (51 citations)
- Towards Scalable 3D Anomaly Detection and Localization: A Benchmark via 3D Anomaly Synthesis and A Self-Supervised Learning Network (51 citations)
- Visual Point Cloud Forecasting enables Scalable Autonomous Driving (51 citations)
- Text2Loc: 3D Point Cloud Localization from Natural Language (46 citations)
- Tri-Perspective View Decomposition for Geometry-Aware Depth Completion (42 citations)
- Point Cloud Pre-training with Diffusion Models (41 citations)
- Dynamic Adapter Meets Prompt Tuning: Parameter-Efficient Transfer Learning for Point Cloud Analysis (35 citations)
and 44 more in the interactive map.
Shape and surface completion · 20 papers
- Point2CAD: Reverse Engineering CAD Models from 3D Point Clouds (42 citations)
- A Conditional Denoising Diffusion Probabilistic Model for Point Cloud Upsampling (32 citations)
- RepKPU: Point Cloud Upsampling with Kernel Point Representation and Deformation (29 citations)
- Scaling Diffusion Models to Real-World 3D LiDAR Scene Completion (28 citations)
- StraightPCF: Straight Point Cloud Filtering (20 citations)
- SPU-PMD: Self-Supervised Point Cloud Upsampling via Progressive Mesh Deformation (18 citations)
- Unsupervised Occupancy Learning from Sparse Point Cloud (15 citations)
- TIGER: Time-Varying Denoising Model for 3D Point Cloud Generation with Diffusion Process (14 citations)
- 3D LiDAR Mapping in Dynamic Environments using a 4D Implicit Neural Representation (13 citations)
- FSC: Few-point Shape Completion (12 citations)
- Motion2VecSets: 4D Latent Vector Set Diffusion for Non-rigid Shape Reconstruction and Tracking (9 citations)
- Small Steps and Level Sets: Fitting Neural Surface Models with Point Guidance (8 citations)
and 8 more in the interactive map.
Segmentation and detection · 16 papers
- OneFormer3D: One Transformer for Unified Point Cloud Segmentation (142 citations)
- OA-CNNs: Omni-Adaptive Sparse CNNs for 3D Semantic Segmentation (66 citations)
- Rethinking Few-shot 3D Point Cloud Semantic Segmentation (48 citations)
- GroupContrast: Semantic-aware Self-supervised Representation Learning for 3D Understanding (23 citations)
- PTT: Point-Trajectory Transformer for Efficient Temporal 3D Object Detection (19 citations)
- Spherical Mask: Coarse-to-Fine 3D Point Cloud Instance Segmentation with Spherical Representation (18 citations)
- TASeg: Temporal Aggregation Network for LiDAR Semantic Segmentation (18 citations)
- ODIN: A Single Model for 2D and 3D Segmentation (17 citations)
- LiSA: LiDAR Localization with Semantic Awareness (14 citations)
- Weakly Supervised Point Cloud Semantic Segmentation via Artificial Oracle (14 citations)
- FreePoint: Unsupervised Point Cloud Instance Segmentation (13 citations)
- Density-Guided Semi-Supervised 3D Semantic Segmentation with Dual-Space Hardness Sampling (12 citations)
and 4 more in the interactive map.
Registration and matching · 10 papers
- FastMAC: Stochastic Spectral Sampling of Correspondence Graph (27 citations)
- Dynamic Cues-Assisted Transformer for Robust Point Cloud Registration (25 citations)
- Inlier Confidence Calibration for Point Cloud Registration (24 citations)
- Extend Your Own Correspondences: Unsupervised Distant Point Cloud Registration by Progressive Distance Extension (22 citations)
- Learning Instance-Aware Correspondences for Robust Multi-Instance Point Cloud Registration in Cluttered Scenes (18 citations)
- ColorPCR: Color Point Cloud Registration with Multi-Stage Geometric-Color Fusion (16 citations)
- Scalable 3D Registration via Truncated Entry-wise Absolute Residuals (12 citations)
- Multiway Point Cloud Mosaicking with Diffusion and Global Optimization (11 citations)
- Coupled Laplacian Eigenmaps for Locally-Aware 3D Rigid Point Cloud Matching (6 citations)
- SG-PGM: Partial Graph Matching Network with Semantic Geometric Fusion for 3D Scene Graph Alignment and Its Downstream Tasks (6 citations)