SAM 3: Segment Anything with Concepts | VitaVision
PaperarXiv (Cornell University) · 2025

SAM 3: Segment Anything with Concepts

Nicolas CarionLaura GustafsonYuan-Ting HuShoubhik DebnathRonghang HuDidac SurisChaitanya K. RyaliKalyan Vasudev AlwalaHaitham KhedrAndrew C. HuangJie LeiTengyu MaBaishan GuoArpit KallaM. David MarksJoseph GreerMeng WangPeize SunRoman RädleTriantafyllos AfourasEffrosyni MavroudiKang XuTsung‐Han WuYu ZhouLiliane MomeniRishi HazraShuangrui DingSagar VazeFrancois PorcherLi FengSiyuan LiAishwarya KamathHao ChengPiotr DollárNikhila RaviKate SaenkoPengchuan ZhangChristoph Feichtenhofer
arXiv 2511.16719DOI
0pages built on it
1more page cites it
3narratives
0registry papers cite it

In the Atlas

Cited as a reference by 1 page, grouped by domain

Segmentation 1
SAM

Appears in 3 narratives

NarrativeFoundation Models for VisionNarrativeSegmentation, from Energy to PromptNarrativeWhere Did the Inductive Bias Go?

Lineage

Papers in the Atlas registry only · one dot per paper
Built upon by · 0
’23’24’25Segment Anything (2023)SAM 2: Segment Anything in Images and Videos (2024)
Built upon by · 0