point clouds
Sets of data points in space representing the external surface of an object, typically obtained from 3D scanning. Point clouds are crucial for tasks like 3D reconstruction, object recognition, and scene understanding.
- Adaptive 3D Reconstruction via Diffusion Priors and Forward Curvature-Matching Likelihood Updates
- CosmoBench: A Multiscale, Multiview, Multitask Cosmology Benchmark for Geometric Deep Learning
- Equivariant Eikonal Neural Networks: Grid-Free, Scalable Travel-Time Prediction on Homogeneous Spaces
- Fully Dynamic Algorithms for Chamfer Distance
- Learning CAD Modeling Sequences via Projection and Part Awareness
- Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors
- MeshCoder: LLM-Powered Structured Mesh Code Generation from Point Clouds
- Modeling Microenvironment Trajectories on Spatial Transcriptomics with NicheFlow
- PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
- Probing Equivariance and Symmetry Breaking in Convolutional Networks
- RIGNO: A Graph-based Framework For Robust And Accurate Operator Learning For PDEs On Arbitrary Domains
- SSR: Enhancing Depth Perception in Vision-Language Models via Rationale-Guided Spatial Reasoning
- U-CAN: Unsupervised Point Cloud Denoising with Consistency-Aware Noise2Noise Matching