ParticleSplat: Self-supervised Object-centric Latent Particle Splatting

2026-09-16

AI Summary

本文提出ParticleSplat方法，通过3D高斯点绘将场景分解为语义实体的潜在'粒子'，解决了Deep Latent Particles框架无法进行显式3D空间和几何推理的问题。

Abstract

We present ParticleSplat, a self-supervised object-centric learning method that decomposes scenes into a set of latent ''particles'' representing semantic entities through feedforward 3D Gaussian Splatting. Building on the Deep Latent Particles (DLP) framework, which represents images as a set of particles with attributes such as position, scale, and visual appearance, we address a key limitation of DLP: its inherently 2D nature, which prevents explicit 3D spatial and geometric reasoning that are critical for downstream tasks such as robotic manipulation. Leveraging the structural similarity between latent particles and 3D Gaussian primitives, we introduce a 3D latent particle space trained with a novel view synthesis objective. Our model jointly encodes multiple views with camera poses into a shared 3D object-centric latent space, then transforms particles into particle-aligned 3D Gaussians whose composition reconstructs the full scene. On simulated and real-world datasets, we show that this formulation inherently learns object masks without supervision and supports controllable 3D scene editing, such as moving objects by modifying particles in the latent space. We further establish that the learned 3D representation improves downstream performance on robotic manipulation tasks.

Problem

• 3D spatial reasoning
• geometric reasoning
• robotic manipulation
• self-supervised learning
• object-centric

Innovation

• Self-supervised Learning
• 3D Gaussian Splatting
• Latent Particle Space
• Object-centric Representation
• Unsupervised Object Mask Learning