ICCV 2023 accepted papers on Point clouds
112 of the 2,156 papers accepted at ICCV 2023 (5.2%) are on Point clouds, compared with 6.3% at ICCV 2021. They fall into 4 topics.
See ICCV 2023 in the interactive map
Submitting to ICCV? Checklist →
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
Point cloud classification · 40 papers
- PointCLIP V2: Prompting CLIP and GPT for Powerful 3D Open-world Learning (284 citations)
- Point-SLAM: Dense Neural Point Cloud-based SLAM (278 citations)
- CLIP2Point: Transfer CLIP to Point Cloud Classification with Image-Depth Pre-Training (193 citations)
- Point-Query Quadtree for Crowd Counting, Localization, and More (112 citations)
- BEVPlace: Learning LiDAR-based Place Recognition using Bird's Eye View Images (107 citations)
- CASSPR: Cross Attention Single Scan Place Recognition (93 citations)
- Implicit Autoencoder for Point-Cloud Self-Supervised Representation Learning (76 citations)
- Instance-aware Dynamic Prompt Tuning for Pre-trained Point Cloud Models (54 citations)
- Clustering based Point Cloud Representation Learning for 3D Analysis (47 citations)
- MBPTrack: Improving 3D Point Cloud Tracking with Memory Networks and Box Priors (38 citations)
- Take-A-Photo: 3D-to-2D Generative Pre-training of Point Cloud Models (36 citations)
- Ponder: Point Cloud Pre-training via Neural Rendering (34 citations)
and 28 more in the interactive map.
Segmentation and detection · 37 papers
- Rethinking Range View Representation for LiDAR Segmentation (195 citations)
- Efficient 3D Semantic Segmentation with Superpoint Transformer (154 citations)
- UniSeg: A Unified Multi-Modal LiDAR Segmentation Network and the OpenPCSeg Codebase (96 citations)
- GraphAlign: Enhancing Accurate Feature Alignment by Graph matching for Multi-Modal 3D Object Detection (80 citations)
- Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation (72 citations)
- PG-RCNN: Semantic Surface Point Generation for 3D Object Detection (56 citations)
- DetZero: Rethinking Offboard 3D Object Detection with Long-term Sequential Point Clouds (49 citations)
- CPCM: Contextual Point Cloud Modeling for Weakly-supervised Point Cloud Semantic Segmentation (47 citations)
- Domain Generalization of 3D Semantic Segmentation in Autonomous Driving (41 citations)
- Divide and Conquer: 3D Point Cloud Instance Segmentation With Point-Wise Binarization (40 citations)
- Query Refinement Transformer for 3D Instance Segmentation (37 citations)
- Hierarchical Point-based Active Learning for Semi-supervised Point Cloud Semantic Segmentation (33 citations)
and 25 more in the interactive map.
Shape and surface completion · 27 papers
- Diffusion-SDF: Conditional Generative Modeling of Signed Distance Functions (137 citations)
- SVDFormer: Complementing Point Cloud via Self-view Augmentation and Self-structure Dual-generator (76 citations)
- Hyperbolic Chamfer Distance for Point Cloud Completion (74 citations)
- GeoUDF: Surface Reconstruction from 3D Point Clouds via Geometry-guided Distance Representation (67 citations)
- P2C: Self-Supervised Point Cloud Completion from Single Partial Clouds (47 citations)
- Dynamic Point Fields (46 citations)
- Learning a More Continuous Zero Level Set in Unsigned Distance Fields through Level Set Projection (46 citations)
- Sketch and Text Guided Diffusion Model for Colored Point Cloud Generation (43 citations)
- DiffFacto: Controllable Part-Based 3D Point Cloud Generation with Cross Diffusion (41 citations)
- Aggregating Feature Point Cloud for Depth Completion (34 citations)
- GridPull: Towards Scalability in Learning Implicit Representations from 3D Point Clouds (27 citations)
- GECCO: Geometrically-Conditioned Point Diffusion Models (25 citations)
and 15 more in the interactive map.
Registration and matching · 8 papers
- RegFormer: An Efficient Projection-Aware Transformer Network for Large-Scale Point Cloud Registration (91 citations)
- 2D3D-MATR: 2D-3D Matching Transformer for Detection-Free Registration Between Images and Point Clouds (46 citations)
- PointMBF: A Multi-scale Bidirectional Fusion Network for Unsupervised RGB-D Point Cloud Registration (29 citations)
- EP2P-Loc: End-to-End 3D Point to 2D Pixel Localization for Large-Scale Visual Localization (28 citations)
- SIRA-PCR: Sim-to-Real Adaptation for 3D Point Cloud Registration (28 citations)
- Density-invariant Features for Distant Point Cloud Registration (20 citations)
- Rethinking Point Cloud Registration as Masking and Reconstruction (17 citations)
- AutoSynth: Learning to Generate 3D Training Data for Object Point Cloud Registration (2 citations)
