Cover Image

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Chen, Jiahao, Zhang, Zihui, Yang, Yafei, Li, Jinxi, Wei, Shenxing, Sun, Zhixuan, Yang, Bo
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation
by: Zhang, Zihui, et al.
Published: (2026)

GrabS: Generative Embodied Agent for 3D Object Segmentation without Scene Supervision
by: Zhang, Zihui, et al.
Published: (2025)

RayletDF: Raylet Distance Fields for Generalizable 3D Surface Reconstruction from Point Clouds or Gaussians
by: Wei, Shenxing, et al.
Published: (2025)

unMORE: Unsupervised Multi-Object Segmentation via Center-Boundary Reasoning
by: Yang, Yafei, et al.
Published: (2025)

OSN: Infinite Representations of Dynamic 3D Scenes from Monocular Videos
by: Song, Ziyang, et al.
Published: (2024)

ObjView-Bench: Rethinking Difficulty and Deployment for Object-Centric View Planning
by: Pan, Sicong, et al.
Published: (2026)

ObjSplat: Geometry-Aware Gaussian Surfels for Active Object Reconstruction
by: Li, Yuetao, et al.
Published: (2026)

TRACE: Learning 3D Gaussian Physical Dynamics from Multi-view Videos
by: Li, Jinxi, et al.
Published: (2025)

Adapting Segment Anything Model for Unseen Object Instance Segmentation
by: Cao, Rui, et al.
Published: (2024)

OpenObj: Open-Vocabulary Object-Level Neural Radiance Fields with Fine-Grained Understanding
by: Deng, Yinan, et al.
Published: (2024)

Object-centric Task Representation and Transfer using Diffused Orientation Fields
by: Bilaloglu, Cem, et al.
Published: (2025)

Informative Object-centric Next Best View for Object-aware 3D Gaussian Splatting in Cluttered Scenes
by: Jeong, Seunghoon, et al.
Published: (2026)

LogoSP: Local-global Grouping of Superpoints for Unsupervised Semantic Segmentation of 3D Point Clouds
by: Zhang, Zihui, et al.
Published: (2025)

STORM: Slot-based Task-aware Object-centric Representation for robotic Manipulation
by: Chapin, Alexandre, et al.
Published: (2026)

$\mathcal{D(R,O)}$ Grasp: A Unified Representation of Robot and Object Interaction for Cross-Embodiment Dexterous Grasping
by: Wei, Zhenyu, et al.
Published: (2024)

FreeGave: 3D Physics Learning from Dynamic Videos by Gaussian Velocity
by: Li, Jinxi, et al.
Published: (2025)

SemanticFlow: A Self-Supervised Framework for Joint Scene Flow Prediction and Instance Segmentation in Dynamic Environments
by: Chen, Yinqi, et al.
Published: (2025)

Object-centric Reconstruction and Tracking of Dynamic Unknown Objects using 3D Gaussian Splatting
by: Barad, Kuldeep R, et al.
Published: (2024)

EvTTC: An Event Camera Dataset for Time-to-Collision Estimation
by: Sun, Kaizhen, et al.
Published: (2024)

OW-Rep: Open World Object Detection with Instance Representation Learning
by: Lee, Sunoh, et al.
Published: (2024)

Object-centric 3D Motion Field for Robot Learning from Human Videos
by: Yin, Zhao-Heng, et al.
Published: (2025)

STRIVE: Structured Representation Integrating VLM Reasoning for Efficient Object Navigation
by: Zhu, Haokun, et al.
Published: (2025)

HyperTASR: Hypernetwork-Driven Task-Aware Scene Representations for Robust Manipulation
by: Sun, Li, et al.
Published: (2025)

Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning
by: Wang, Jiaxu, et al.
Published: (2024)

Self-Supervised Monocular 4D Scene Reconstruction for Egocentric Videos
by: Yuan, Chengbo, et al.
Published: (2024)

ArtiSG: Functional 3D Scene Graph Construction via Human-demonstrated Articulated Objects Manipulation
by: Gu, Qiuyi, et al.
Published: (2025)

TOSS: Real-time Tracking and Moving Object Segmentation for Static Scene Mapping
by: Jang, Seoyeon, et al.
Published: (2024)

SceneFactory: A Workflow-centric and Unified Framework for Incremental Scene Modeling
by: Yuan, Yijun, et al.
Published: (2024)

Weakly Supervised Point Clouds Transformer for 3D Object Detection
by: Tang, Zuojin, et al.
Published: (2023)

Clutt3R-Seg: Sparse-view 3D Instance Segmentation for Language-grounded Grasping in Cluttered Scenes
by: Noh, Jeongho, et al.
Published: (2026)

OpenVox: Real-time Instance-level Open-vocabulary Probabilistic Voxel Representation
by: Deng, Yinan, et al.
Published: (2025)

Object-Scene-Camera Decomposition and Recomposition for Data-Efficient Monocular 3D Object Detection
by: Kuang, Zhaonian, et al.
Published: (2026)

EMPM: Embodied MPM for Modeling and Simulation of Deformable Objects
by: Chen, Yunuo, et al.
Published: (2026)

RecoverFormer: End-to-End Contact-Aware Recovery for Humanoid Robots
by: Liu, Zihui
Published: (2026)

Grasp Anything: Combining Teacher-Augmented Policy Gradient Learning with Instance Segmentation to Grasp Arbitrary Objects
by: Mosbach, Malte, et al.
Published: (2024)

3D Multi-Object Tracking with Semi-Supervised GRU-Kalman Filter
by: Wang, Xiaoxiang, et al.
Published: (2024)

C-NAV: Towards Self-Evolving Continual Object Navigation in Open World
by: Yu, Ming-Ming, et al.
Published: (2025)

End-to-End Dexterous Grasp Learning from Single-View Point Clouds via a Multi-Object Scene Dataset
by: Geng, Tao, et al.
Published: (2026)

Learning Autonomous Surgical Irrigation and Suction with the da Vinci Research Kit Using Reinforcement Learning
by: Ou, Yafei, et al.
Published: (2024)

PhysInOne: Visual Physics Learning and Reasoning in One Suite
by: Zhou, Siyuan, et al.
Published: (2026)