ICLR 2026 accepted papers on Point clouds
23 of the 5,358 papers accepted at ICLR 2026 (0.4%) are on Point clouds, compared with 0.7% at ICLR 2025. They fall into 4 topics.
See ICLR 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 · 12 papers
- Adaptive Canonicalization with Application to Invariant Anisotropic Geometric Networks
- Change Point Localization and Inference in Dynamic Multilayer Networks
- CLAP: Unsupervised 3D Representation Learning for Fusion 3D Perception via Curvature Sampling and Prototype Learning
- Exploring the Potential of Encoder-free Architectures in 3D LMMs
- Sparkle: A Robust and Versatile Representation for Point Cloud-based Human Motion Capture
- 3DSMT: A Hybrid Spiking Mamba-Transformer for Point Cloud Analysis
- EquAct: An SE(3)-Equivariant Multi-Task Transformer for 3D Robotic Manipulation
- Low-Latency Neural LiDAR Compression with 2D Context Models
- On the Spectral Differences Between NTK and CNTK and Their Implications for Point Cloud Recognition
- Point-Focused Attention Meets Context-Scan State Space: Robust Biological Visual Perception for Point Cloud Representation
- Spiking Discrepancy Transformer for Point Cloud Analysis
- Test-Time Optimization of 3D Point Cloud LLM via Manifold-Aware In-Context Guidance and Refinement
Segmentation and detection · 5 papers
- Adaptive Augmentation-Aware Latent Learning for Robust LiDAR Semantic Segmentation
- GeoPurify: A Data-Efficient Geometric Distillation Framework for Open-Vocabulary 3D Segmentation
- Point-MoE: Large-Scale Multi-Dataset Training with Mixture-of-Experts for 3D Semantic Segmentation
- GOOD: Geometry-guided Out-of-Distribution Modeling for Open-set Test-time Adaptation in Point Cloud Semantic Segmentation
- PTNET: A PROPOSAL-CENTRIC TRANSFORMER NET- WORK FOR 3D OBJECT DETECTION
Shape and surface completion · 5 papers
- Quartet of Diffusions: Structure-Aware Point Cloud Generation through Part and Symmetry Guidance
- Guaranteed Simply Connected Mesh Reconstruction from an Unorganized Point Cloud
- MoGen: Detailed Neuronal Morphology Generation via Point Cloud Flow Matching
- Neural Compression of 3D Meshes using Sparse Implicit Representation
- Parameterization-Based Dataset Distillation of 3D Point Clouds through Learnable Shape Morphing