ParticleSplat: Self-supervised Object-centric Latent Particle Splatting
cs.CV, cs.RO
Submitted: 2026-09-16
Updated: 2026-09-16
Project page: https://lyuxinghe.github.io/ParticleSplat-website
Terminology
Sources
- GraspSplats: Efficient Manipulation with 3D Feature Splatting
- MONet: Unsupervised Scene Decomposition and Representation
- Act3D: 3D Feature Field Transformers for Multi-Task Robotic Manipulation
- RVT-2: Learning Precise Manipulation from Few Demonstrations
- Object Scene Representation Transformer
- Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
- Decomposing 3D Scenes into Objects via Unsupervised Volume Segmentation
- Equivariant Diffusion Policy
- VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
- SPACE: Unsupervised Object-Oriented Scene Representation via Spatial Attention and Decomposition
- Object-Centric Learning with Slot Attention
- Stereo Magnification: Learning View Synthesis using Multiplane Images
- 3D Diffusion Policy: Generalizable Visuomotor Policy Learning via Simple 3D Representations
- Learning Geometrically-Grounded Amodal 3D Representations for View-Generalizable Robotic Manipulation
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models