camouflaged object segmentation 1cross-image prompting 1foundation models 1referring object detection 1training-free methods 1
From the 1 of 2 linked papers with an AI index.
2 papers
cs.CV2026
GFR-SAM: Training-Free Referring Camouflaged Object Segmentation via Cross-Image Prompting
Yilong Yang, Jianxin Tian, Shengchuan Zhang +1
The paper introduces GFR‑SAM, a training‑free three‑stage framework that uses cross‑image prompting with SAM3 to segment camouflaged objects referenced by cues, employing exemplar‑…
cs.CV2026
Discover, Segment, and Select: A Progressive Mechanism for Zero-shot Camouflaged Object Segmentation
Yilong Yang, Jianxin Tian, Shengchuan Zhang +1
Current zero-shot Camouflaged Object Segmentation methods typically employ a two-stage pipeline (discover-then-segment): using MLLMs to obtain visual prompts, followed by SAM segme…