IP-SAM allows the Segment Anything Model (SAM) to perform automatic, prompt-free segmentation by generating its own 'intrinsic prompts'.
March 31, 2026
Original Paper
IP-SAM: Prompt-Space Conditioning for Prompt-Absent Camouflaged Object Detection
arXiv · 2603.27250
The Takeaway
It bridges the gap between interactive foundation models and fully automated deployment. By using the model's native prompt interface for self-guidance rather than bypassing it, it achieves SOTA results on difficult camouflaged object detection tasks without human intervention.
From the abstract
Prompt-conditioned foundation segmenters have emerged as a dominant paradigm for image segmentation, where explicit spatial prompts (e.g., points, boxes, masks) guide mask decoding. However, many real-world deployments require fully automatic segmentation, creating a structural mismatch: the decoder expects prompts that are unavailable at inference. Existing adaptations typically modify intermediate features, inadvertently bypassing the model's native prompt interface and weakening prompt-condit