ICLR 2024 accepted papers on Point clouds
18 of the 2,259 papers accepted at ICLR 2024 (0.8%) are on Point clouds, compared with 0.7% at ICLR 2023. They fall into 4 topics.
See ICLR 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 · 11 papers
- Uni3D: Exploring Unified 3D Representation at Scale (9 citations)
- 3D Feature Prediction for Masked-AutoEncoder-Based Point Cloud Pretraining (5 citations)
- Fast, Expressive $\mathrm{SE}(n)$ Equivariant Networks through Weight-Sharing in Position-Orientation Space (5 citations)
- Symbol as Points: Panoptic Symbol Spotting via Point-based Representation (2 citations)
- Differentiable Euler Characteristic Transforms for Shape Classification (1 citation)
- Approximately Piecewise E(3) Equivariant Point Networks
- Decodable and Sample Invariant Continuous Object Encoder
- OpenNeRF: Open Set 3D Neural Scene Segmentation with Pixel-Wise Features and Rendered Novel Views
- Quasi-Monte Carlo for 3D Sliced Wasserstein
- ZeroFlow: Scalable Scene Flow via Distillation
- DeepSPF: Spherical SO(3)-Equivariant Patches for Scan-to-CAD Estimation
Segmentation and detection · 4 papers
- AGILE3D: Attention Guided Interactive Multi-object 3D Segmentation (5 citations)
- LiDAR-PTQ: Post-Training Quantization for Point Cloud 3D Object Detection (4 citations)
- Multi-View Representation is What You Need for Point-Cloud Pre-Training
- Pre-training LiDAR-based 3D Object Detectors through Colorization