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.
By Lyuxing He, Daniel Guo, Elizabeth Terveen, Deepak Pathak, David Held, Tal Daniel
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.
By Boshi Li, Xiaohui Wang, Xiaoyang Wu, Zhichao Li, Ya Yang, Naiyan Wang
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 Spla...
arXiv:2609.39785v1 Announce Type: new
Abstract: The Segment Anything Model (SAM) relies heavily on massive manual annotations, creating a fundamental bottleneck for model scaling. While unsupervised...
By Weijian Jian, Xiaoyue Zhang, Bin Xiao, Chunyu Xie, Yixiao He, Yutao Liu, Dawei Leng, Yuhui Yin
arXiv:2503. 24009v3 Announce Type: replace-cross Abstract: Realistic simulation is critical for applications ranging from robotics to animation.
By Mikel Zhobro, Andreas Ren\'e Geist, Georg Martius
arXiv:2609.07174v1 Announce Type: new
Abstract: Efficient, fully automatic, and physically plausible 4D Gaussian synthesis is an important goal for dynamic scene generation. Recent physics-based meth...
By Jiang Qin, Chunji Lv, Yangguang Wei, Yang Gao, Ming Liu, Lizhong Ding, Ye Yuan, Yinjie Lei, Changsheng Li
arXiv:2609.36940v1 Announce Type: new
Abstract: Accurate dynamic scene reconstruction is important for robotic perception, where temporally consistent representations of dynamic environments are esse...
By Thai Duy Nguyen, Haitian Zhang, Addison Lin Wang
arXiv:2608.20770v1 Announce Type: new
Abstract: Modern AI video generation models can produce videos with high visual fidelity and seemingly smooth temporal transitions. However, visual realism does...
By Haojin He, Hao Tan, Zichang Tan, Ajian Liu, Jun Wan
arXiv:2606. 29531v1 Announce Type: cross Abstract: We propose MotionAtlas, a system for detailed captioning of motion-centric videos, comprising (1) a dedicated human-annotated benchmark, (2) a scalable, high-quality pipeline to construct training samples, and (3) a family of powerful Video-MLLMs.
By Weisong Liu, Haochen Wang, Kuan Gao, Yuhao Wang, Yikang Zhou, Zhongwei Ren, Jacky Mai, Anna Wang, Yanwei Li, Jason Li, Zhaoxiang Zhang
MoSE3 is a feed‑forward model that predicts dense SE(3) motion—full 6‑DoF rigid transforms—at every pixel from monocular RGB video, providing rotation, translation, and grouping information simultaneously. It achieves this by jointly learning 3D point tracks and rigidity embeddings, then differentiably fitting transforms within soft rigid clusters. The authors also release Art‑Kubric, a large synthetic dataset with dense SE(3) and rigidity labels, and demonstrate state‑of‑the‑art performance on both rigid and articulated benchmarks, with strong generalization to real‑world videos.
By Jiahuan Cheng, Zhiyi Li, Tian Xia, Ruojin Cai, Yilun Du, Qianqian Wang
arXiv:2608.23279v1 Announce Type: new
Abstract: Text-driven human motion synthesis has made substantial development with two core modules of motion representation and generative architecture. For rep...
By Chengqun Yang, Liang Xu, Yanping Li, Fulong Liu, Jingnan Gao, Weili Zeng, Yichao Yan
SCION introduces a hierarchical compositional scene representation that replaces independent Gaussians with a compact vocabulary of reusable primitives and lightweight world-space instances. By jointly optimizing discrete and continuous scene parameters, SCION achieves high-quality reconstructions at a small size (≈1.2 MB) and outperforms existing Gaussian compression methods in rate‑distortion. The approach enables instance‑level editing and animation without retraining, demonstrating that neural scene representations can discover reusable parts instead of memorizing each element separately.
By William Koch, Amogh Joshi, Cyrus Vachha, Cheng Zheng, Felix Heide