ICML 2026 accepted papers on Point clouds
29 of the 6,341 papers accepted at ICML 2026 (0.5%) are on Point clouds, compared with 0.6% at ICML 2025. They fall into 4 topics.
See ICML 2026 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 · 18 papers
- Scalable Event Cloud Network for Event-based Classification (1 citation)
- 4DPC$^2$hat: Towards Dynamic Point Cloud Understanding with Failure-Aware Bootstrapping
- Any3D-VLA: Enhancing VLA Robustness via Diverse Point Clouds
- DynaTok: Token-Based 4D Reconstruction from Partial Point Clouds
- EPiC: Efficient Video Camera Control Learning with Precise Anchor-Video Guidance
- PACE: Post-Causal Entropy Modeling for Learned LiDAR Point Cloud Compression
- PointCHR: Point Cloud Analysis via Curvature-Aware Hyperbolic Rectification
- SplAttN: Bridging 2D and 3D with Gaussian Soft Splatting and Attention for Point Cloud Completion
- Utonia: Toward One Encoder for All Point Clouds
- Bridging Tokens and Geometry: Token-wise 3D Supervision for CAD Generation
- Dimensionality Reduction with Point-distributions Similarity Invariant
- FlowCloud: Learning Continuous Spatiotemporal Dynamics from Unpaired Sparse Point Cloud Snapshots
and 6 more in the interactive map.
Shape and surface completion · 6 papers
- Metric—Phase Fields: Decoupling Distance and Sign for Thin-Structure Reconstruction from Unoriented Point Clouds
- Rethinking 3D Shape Generation: Diffusion over Superquadrics
- SIMPC: Learning Self-Induced Mirror-Point Consistency for Unsupervised Point Cloud Denoising
- 3D MeanFlow: One-Step Point Cloud Completion and Generation via Average-Velocity Transport
- NoiseSDF2NoiseSDF: Learning Clean Neural Fields from Noisy Supervision
- Towards Docking-oriented De Novo Ligand Design via Gradient Inversion