From tokens to concepts: how particle models perceive the world

What this post added

Introduces 3D-DLP, a novel self-supervised approach for learning 3D object-centric scene representations. Key technical contributions include extending Deep Latent Particles (DLPs) to 3D, developing an appearance-aware K-means prior to address issues with sparse voxel grids, and implementing a chroma loss for accurate color reconstruction. The post also details experimental validation showing the superiority of 3D-DLP over baselines in manipulation tasks.