NeurIPS 2022 accepted papers on Point clouds
40 of the 2,901 papers accepted at NeurIPS 2022 (1.4%) are on Point clouds, compared with 0.9% at NeurIPS 2021. They fall into 4 topics.
See NeurIPS 2022 in the interactive map
Submitting to NeurIPS? 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 · 14 papers
- PointNeXt: Revisiting PointNet++ with Improved Training and Scaling Strategies (415 citations)
- Point Transformer V2: Grouped Vector Attention and Partition-based Pooling (195 citations)
- Point-M2AE: Multi-scale Masked Autoencoders for Hierarchical Point Cloud Pre-training (117 citations)
- P2P: Tuning Pre-trained Image Models for Point Cloud Analysis with Point-to-Pixel Prompting (36 citations)
- Rethinking the compositionality of point clouds through regularization in the hyperbolic space (17 citations)
- Language Conditioned Spatial Relation Reasoning for 3D Object Grounding (14 citations)
- Look Around and Refer: 2D Synthetic Semantics Knowledge Distillation for 3D Visual Grounding (13 citations)
- On the Effectiveness of Persistent Homology (13 citations)
- SageMix: Saliency-Guided Mixup for Point Clouds (12 citations)
- Change-point Detection for Sparse and Dense Functional Data in General Dimensions (5 citations)
- Let Images Give You More: Point Cloud Cross-Modal Training for Shape Analysis (2 citations)
- Geodesic Self-Attention for 3D Point Clouds
and 2 more in the interactive map.
Segmentation and detection · 12 papers
- BEVFusion: A Simple and Robust LiDAR-Camera Fusion Framework (201 citations)
- Fully Convolutional One-Stage 3D Object Detection on LiDAR Range Images (60 citations)
- PolarMix: A General Data Augmentation Technique for LiDAR Point Clouds (37 citations)
- OGC: Unsupervised 3D Object Segmentation from Rigid Dynamics of Point Clouds (10 citations)
- Sparse2Dense: Learning to Densify 3D Features for 3D Object Detection (8 citations)
- 4D Unsupervised Object Discovery (7 citations)
- Prototypical VoteNet for Few-Shot 3D Point Cloud Object Detection (6 citations)
- Joint Learning of 2D-3D Weakly Supervised Semantic Segmentation (2 citations)
- Learning Superpoint Graph Cut for 3D Instance Segmentation (2 citations)
- MsSVT: Mixed-scale Sparse Voxel Transformer for 3D Object Detection on Point Clouds (2 citations)
- Self-Supervised Pretraining for Large-Scale Point Clouds
- 3DOS: Towards 3D Open Set Learning - Benchmarking and Understanding Semantic Novelty Detection on Point Clouds
Shape and surface completion · 12 papers
- LION: Latent Point Diffusion Models for 3D Shape Generation (190 citations)
- Cross-modal Learning for Image-Guided Point Cloud Shape Completion (19 citations)
- Diffusion-based Molecule Generation with Informative Prior Bridges (19 citations)
- HSurf-Net: Normal Estimation for 3D Point Clouds by Learning Hyper Surfaces (16 citations)
- GenSDF: Two-Stage Learning of Generalizable Signed Distance Functions (12 citations)
- SNAKE: Shape-aware Neural 3D Keypoint Field (8 citations)
- Learning Consistency-Aware Unsigned Distance Functions Progressively from Raw Point Clouds (5 citations)
- NCP: Neural Correspondence Prior for Effective Unsupervised Shape Matching (3 citations)
- Diffusion Curvature for Estimating Local Curvature in High Dimensional Data (1 citation)
- HSDF: Hybrid Sign and Distance Field for Modeling Surfaces with Arbitrary Topologies (1 citation)
- SPoVT: Semantic-Prototype Variational Transformer for Dense Point Cloud Semantic Completion
- Unsupervised Point Cloud Completion and Segmentation by Generative Adversarial Autoencoding Network
