Hugging Face Trending Papers
ParticleSplat: Self-supervised Object-centric Latent Particle Splatting
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Sep 18
ParticleSplat: Self-supervised Object-centric Latent Particle Splatting
ParticleSplat is a self‑supervised, object‑centric learning framework that extends the Deep Latent Particles (DLP) model into 3D by representing scenes as latent particles mapped to 3D Gaussian splats. It jointly encodes multiple camera views into a shared 3D latent space, enabling unsupervised learning of object masks and controllable 3D scene editing such as moving objects by manipulating latent particles. Experiments on simulated and real‑world datasets demonstrate that this 3D representation improves performance on downstream robotic manipulation tasks.
arXiv Machine Learning
Jun 19
3D-DLP: Self-Supervised 3D Object-Centric Scene Representation Learning
arXiv:2606. 19451v1 Announce Type: new Abstract: We introduce 3D-DLP, a self-supervised object-centric representation learning model that decomposes scene-level RGB-D or voxel observations into a set of 3D latent particles.
arXiv AI
Jul 3
Learning 3D-Gaussian Simulators from RGB Videos
arXiv:2503. 24009v3 Announce Type: replace-cross Abstract: Realistic simulation is critical for applications ranging from robotics to animation.
arXiv AI
Jun 29
GenMatter: Perceiving Physical Objects with Generative Matter Models
arXiv:2604. 22160v2 Announce Type: replace-cross Abstract: Human visual perception offers valuable insights for understanding computational principles of motion-based scene interpretation.
Hugging Face Trending Papers
Aug 6
LAWM-3D: Learning 3D-Aware Latent Actions from Human Videos for Generalizable Robot World Models
World models enable agents to perform forward rollout and planning without real-world interaction. However, their application in open-world embodied intelligence remains limited by the high cost of action annotations and the heterogeneity of action spaces across platforms.
arXiv Computer Vision
Sep 7
Object Concepts Emerge from Motion
The paper introduces a biologically inspired framework that learns object‑centric visual representations from raw videos without human annotations or camera calibration. By using motion boundaries detected via optical flow and clustering to create pseudo‑instance masks, the method supervises a single‑image encoder with pixel‑level pairwise metric learning. Training on 195 million pseudo‑labeled frames and expanding to 421 million frames through Motion‑Verified Self‑Training, the approach yields Swin‑based encoders that outperform or match supervised and self‑supervised baselines on tasks such as monocular depth estimation, 3D object detection, 3D occupancy prediction, and end‑to‑end planning.