Cover Image

InstructSAM: Segment Any Instance with Any Instructions

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Yuan, Yuqian, Li, Wentong, Li, Zhaocheng, Lin, Yutong, Li, Juncheng, Tang, Siliang, Xiao, Jun, Zhuang, Yueting, Zhang, Wenqiao
Format:	Preprint
Published:	2026
Subjects:	Computer Vision and Pattern Recognition
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

AnyMS: Bottom-up Attention Decoupling for Layout-guided and Training-free Multi-subject Customization
by: Yu, Binhe, et al.
Published: (2025)

InstructVid2Vid: Controllable Video Editing with Natural Language Instructions
by: Qin, Bosheng, et al.
Published: (2023)

InstructSAM: A Training-Free Framework for Instruction-Oriented Remote Sensing Object Recognition
by: Zheng, Yijie, et al.
Published: (2025)

AnyEdit: Mastering Unified High-Quality Image Editing for Any Idea
by: Yu, Qifan, et al.
Published: (2024)

Robust Modality-incomplete Anomaly Detection: A Modality-instructive Framework with Benchmark
by: Miao, Bingchen, et al.
Published: (2024)

CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
by: Wang, Wei, et al.
Published: (2026)

Insight Any Instance: Promptable Instance Segmentation for Remote Sensing Images
by: Li, Xuexue
Published: (2024)

LMMs Meet Object-Centric Vision: Understanding, Segmentation, Editing and Generation
by: Yuan, Yuqian, et al.
Published: (2026)

SOYO: A Tuning-Free Approach for Video Style Morphing via Style-Adaptive Interpolation in Diffusion Models
by: Zheng, Haoyu, et al.
Published: (2025)

Fine-tuning Multimodal LLMs to Follow Zero-shot Demonstrative Instructions
by: Li, Juncheng, et al.
Published: (2023)

EOC-Bench: Can MLLMs Identify, Recall, and Forecast Objects in an Egocentric World?
by: Yuan, Yuqian, et al.
Published: (2025)

OmniMoGen: Unifying Human Motion Generation via Learning from Interleaved Text-Motion Instructions
by: Bu, Wendong, et al.
Published: (2025)

SpatialFusion: Endowing Unified Image Generation with Intrinsic 3D Geometric Awareness
by: Qiu, Haiyi, et al.
Published: (2026)

InstructAny2Pix: Flexible Visual Editing via Multimodal Instruction Following
by: Li, Shufan, et al.
Published: (2023)

Tarot-SAM3: Training-free SAM3 for Any Referring Expression Segmentation
by: Zhang, Weiming, et al.
Published: (2026)

Compress Any Segment Anything Model (SAM)
by: Fan, Juntong, et al.
Published: (2025)

X-SAM: From Segment Anything to Any Segmentation
by: Wang, Hao, et al.
Published: (2025)

CORE: Code-based Inverse Self-Training Framework with Graph Expansion for Virtual Agents
by: Wang, Keyu, et al.
Published: (2026)

Mastering Collaborative Multi-modal Data Selection: A Focus on Informativeness, Uniqueness, and Representativeness
by: Yu, Qifan, et al.
Published: (2024)

LASER: Tuning-Free LLM-Driven Attention Control for Efficient Text-conditioned Image-to-Animation
by: Zheng, Haoyu, et al.
Published: (2024)

Fact :Teaching MLLMs with Faithful, Concise and Transferable Rationales
by: Gao, Minghe, et al.
Published: (2024)

X2SAM: Any Segmentation in Images and Videos
by: Wang, Hao, et al.
Published: (2026)

De-fine: Decomposing and Refining Visual Programs with Auto-Feedback
by: Gao, Minghe, et al.
Published: (2023)

SAI3D: Segment Any Instance in 3D Scenes
by: Yin, Yingda, et al.
Published: (2023)

Instruct2See: Learning to Remove Any Obstructions Across Distributions
by: Li, Junhang, et al.
Published: (2025)

Iris: Breaking GUI Complexity with Adaptive Focus and Self-Refining
by: Ge, Zhiqi, et al.
Published: (2024)

Segment Any Mesh
by: Tang, George, et al.
Published: (2024)

MAKIMA: Tuning-free Multi-Attribute Open-domain Video Editing via Mask-Guided Attention Modulation
by: Zheng, Haoyu, et al.
Published: (2024)

HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data
by: Yu, Qifan, et al.
Published: (2023)

Online Segment Any 3D Thing as Instance Tracking
by: Wang, Hanshi, et al.
Published: (2025)

Segment Any Vehicle: Semantic and Visual Context Driven SAM and A Benchmark
by: Wang, Xiao, et al.
Published: (2025)

MAS-SAM: Segment Any Marine Animal with Aggregated Features
by: Yan, Tianyu, et al.
Published: (2024)

Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs
by: Fan, Zhaoyu, et al.
Published: (2025)

PixelRefer: A Unified Framework for Spatio-Temporal Object Referring with Arbitrary Granularity
by: Yuan, Yuqian, et al.
Published: (2025)

HealthGPT: A Medical Large Vision-Language Model for Unifying Comprehension and Generation via Heterogeneous Knowledge Adaptation
by: Lin, Tianwei, et al.
Published: (2025)

SAM 2++: Tracking Anything at Any Granularity
by: Zhang, Jiaming, et al.
Published: (2025)

Segment Any Medical Model Extended
by: Liu, Yihao, et al.
Published: (2024)

Segment Any Change
by: Zheng, Zhuo, et al.
Published: (2024)

EmbodiedSAM: Online Segment Any 3D Thing in Real Time
by: Xu, Xiuwei, et al.
Published: (2024)

SAGOnline: Segment Any Gaussians Online
by: Sun, Wentao, et al.
Published: (2025)