Imagen de Portada

FoundObj: Self-supervised Foundation Models as Rewards for Label-free 3D Object Segmentation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Zhang, Zihui, Sun, Zhixuan, Yang, Yafei, Li, Jinxi, Chen, Jiahao, Yang, Bo
Formato:	Preprint
Publicado:	2026
Materias:	Computer Vision and Pattern Recognition Artificial Intelligence Machine Learning Robotics
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

EvObj: Learning Evolving Object-centric Representations for 3D Instance Segmentation without Scene Supervision
por: Chen, Jiahao, et al.
Publicado: (2026)

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

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

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

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

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

FoundPose: Unseen Object Pose Estimation with Foundation Features
por: Örnek, Evin Pınar, et al.
Publicado: (2023)

WLST: Weak Labels Guided Self-training for Weakly-supervised Domain Adaptation on 3D Object Detection
por: Tsou, Tsung-Lin, et al.
Publicado: (2023)

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

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

Temporal Overlapping Prediction: A Self-supervised Pre-training Method for LiDAR Moving Object Segmentation
por: Miao, Ziliang, et al.
Publicado: (2025)

FOMO-3D: Using Vision Foundation Models for Long-Tailed 3D Object Detection
por: Yang, Anqi Joyce, et al.
Publicado: (2026)

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

Semantics-Guided Moving Object Segmentation with 3D LiDAR
por: Gu, Shuo, et al.
Publicado: (2022)

A Good Foundation is Worth Many Labels: Label-Efficient Panoptic Segmentation
por: Vödisch, Niclas, et al.
Publicado: (2024)

Learning Shared RGB-D Fields: Unified Self-supervised Pre-training for Label-efficient LiDAR-Camera 3D Perception
por: Xu, Xiaohao, et al.
Publicado: (2024)

MixSup: Mixed-grained Supervision for Label-efficient LiDAR-based 3D Object Detection
por: Yang, Yuxue, et al.
Publicado: (2024)

Adapt2Reward: Adapting Video-Language Models to Generalizable Robotic Rewards via Failure Prompts
por: Yang, Yanting, et al.
Publicado: (2024)

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

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

Scene-Agnostic Traversability Labeling and Estimation via a Multimodal Self-supervised Framework
por: Fang, Zipeng, et al.
Publicado: (2025)

Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models
por: Vankadari, Madhu, et al.
Publicado: (2024)

Label-Efficient 3D Object Detection For Road-Side Units
por: Dao, Minh-Quan, et al.
Publicado: (2024)

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation Models
por: Lu, Ziqi, et al.
Publicado: (2024)

ZISVFM: Zero-Shot Object Instance Segmentation in Indoor Robotic Environments with Vision Foundation Models
por: Zhang, Ying, et al.
Publicado: (2025)

Bridging Perspectives: Foundation Model Guided BEV Maps for 3D Object Detection and Tracking
por: Käppeler, Markus, et al.
Publicado: (2025)

Efficient Image Annotation via Semi-Supervised Object Segmentation with Label Propagation
por: Tutevych, Vitalii, et al.
Publicado: (2026)

Learning Generalizable 3D Manipulation With 10 Demonstrations
por: Ren, Yu, et al.
Publicado: (2024)

GFreeDet: Exploiting Gaussian Splatting and Foundation Models for Model-free Unseen Object Detection in the BOP Challenge 2024
por: Liu, Xingyu, et al.
Publicado: (2024)

DVPE: Divided View Position Embedding for Multi-View 3D Object Detection
por: Wang, Jiasen, et al.
Publicado: (2024)

Lost & Found: Tracking Changes from Egocentric Observations in 3D Dynamic Scene Graphs
por: Behrens, Tjark, et al.
Publicado: (2024)

Improving 3D Labeling in Self-Driving by Inferring Vehicle Information using Vision Language Models
por: Chen, Steven, et al.
Publicado: (2026)

Segment, Lift and Fit: Automatic 3D Shape Labeling from 2D Prompts
por: Li, Jianhao, et al.
Publicado: (2024)

FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects
por: Wen, Bowen, et al.
Publicado: (2023)

Object Segmentation from Open-Vocabulary Manipulation Instructions Based on Optimal Transport Polygon Matching with Multimodal Foundation Models
por: Nishimura, Takayuki, et al.
Publicado: (2024)

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

Few-Shot Panoptic Segmentation With Foundation Models
por: Käppeler, Markus, et al.
Publicado: (2023)

Articulate AnyMesh: Open-Vocabulary 3D Articulated Objects Modeling
por: Qiu, Xiaowen, et al.
Publicado: (2025)

Mars Traversability Prediction: A Multi-modal Self-supervised Approach for Costmap Generation
por: Xie, Zongwu, et al.
Publicado: (2025)

Learning to Identify Out-of-Distribution Objects for 3D LiDAR Anomaly Segmentation
por: Mosco, Simone, et al.
Publicado: (2026)