Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level 3D segmentation. However, the supervision signals from foundation models are not fundamentally object-centric and often require additional mask pre/post-processing or specialized training and loss design to resolve mask identity conflicts across views. The learned identity of the 3D scene is scene-dependent, limiting generalizability across scenes. Therefore, we propose a dataset-level, object-centric supervision scheme to learn object representations in 3D Gaussian Splatting (3DGS). Building on a pre-trained slot attention-based Global Object Centric Learning (GOCL) module, we learn a scene-agnostic object codebook that provides consistent, identity-anchored representations across views and scenes. By coupling the codebook with the module's unsupervised object masks, we can directly supervise the identity features of 3D Gaussians without additional mask pre-/post-processing or explicit multi-view alignment. The learned scene-agnostic codebook enables object supervision and identification without per-scene fine-tuning or retraining. Our method thus introduces unsupervised object-centric learning (OCL) into 3DGS, yielding more structured representations and better generalization for downstream tasks such as robotic interaction, scene understanding, and cross-scene generalization.
Predictive Photometric Uncertainty in Gaussian Splatting for Novel View Synthesis
QUT Centre for Robotics, Australia（昆士兰大学机器人中心，澳大利亚）；ARIAM Hub, Australia（ARIAM中心，澳大利亚）；University of Wuppertal, Germany（乌尔姆大学，德国）；University of Osnabrück, Germany（奥斯纳布吕克大学，德国）
Wangxuan Institute of Computer Technology, Peking University（北京大学计算机技术研究院）；Chongqing Changan Automobile Co., Ltd（重庆长安汽车有限公司）；University of California, Merced（加州大学默塞德分校）
Object-Centric 3D Gaussian Splatting for Strawberry Plant Reconstruction and Phenotyping
Department of Electrical and Computer Engineering, Michigan State University, East Lansing, MI, USA（电气与计算机工程系，密歇根州立大学）；Department of Mechanical Engineering, Michigan State University, East Lansing, MI, USA（机械工程系，密歇根州立大学）；Truck Crops Branch Experiment Station, Mississippi State University, Starkville, MS, USA（卡车作物分支实验站，密苏里州立大学）；Department of Agricultural and Biological Engineering, Mississippi State University, Starkville, MS, USA（农业与生物工程系，密苏里州立大学）；Tandon School of Engineering, New York University, NY, USA（坦顿工程学院，纽约大学）
German Research Center for Artificial Intelligence (DFKI)（德国人工智能研究中心（DFKI））；RPTU University Kaiserslautern-Landau（科布伦茨-兰道大学（RPTU））；University of Modena and Reggio Emilia（摩德纳和雷吉奥-艾米利亚大学）
On the Geometric Accuracy of Implicit and Primitive-based Representations Derived from View Rendering Constraints
KU Leuven, Dept. Electrical Engineering, Research unit Processing Speech and Images（KU莱顿，电气工程系，语音与图像研究单位）；UCLouvain, ICTEAM, Dept. Electrical Engineering（UCLouvain，ICTEAM，电气工程系）；KU Leuven, Dept. Mechanical Engineering, Research unit Robotics, Automation and Mechatronics（KU莱顿，机械工程系，机器人、自动化与机电研究单位）
REArtGS++: Generalizable Articulation Reconstruction with Temporal Geometry Constraint via Planar Gaussian Splatting
Hefei Institutes of Physical Science, Chinese Academy of Sciences（合肥物理科学研究院，中国科学院）；University of Science and Technology of China（中国科学技术大学）；Hefei University of Technology（合肥工业大学）；RoboticsX, Tencent（腾讯机器人院）；Shanghai Jiao Tong University（上海交通大学）
PolarGS: Polarimetric Cues for Ambiguity-Free Gaussian Splatting with Accurate Geometry Recovery
Institute of Artificial Intelligence, Beihang University（北航人工智能研究院）；Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing（北京未来区块链与隐私计算先进创新中心）；State Key Laboratory of Virtual Reality Technology and Systems, School of Computer Science and Engineering, Beihang University（虚拟现实技术与系统国家重点实验室，北航计算机科学与工程学院）
