image-segmentation

Tag

Cards List
#image-segmentation

PANORAMA: Panoptic Grounded Captioning via Mask Proposal Selection

Hugging Face Daily Papers ↗ · 2026-09-16 Cached

The paper presents PANORAMA, a vision-language model for panoptic grounded captioning that uses mask proposal selection to ground captions with pixel-level masks, and introduces the PanoCaps benchmark for evaluation.

0 favorites 0 likes
#image-segmentation

Show HN: MultiMatte, a Promptable Image Background Removal Model

Hacker News Top ↗ · 2026-09-10 Cached

MultiMatte is a promptable image background removal model fine-tuned from SAM 3 using LoRA, achieving higher accuracy on benchmarks by outputting alpha mattes for better handling of fuzzy boundaries.

0 favorites 0 likes
#image-segmentation

@MaximeRivest: this is a really cool and powerful trick for image segmentation with sam without prompting! > You can exploit the small…

X AI KOLs Following ↗ · 2026-08-24 Cached

A technique is shared for using the Segment Anything Model (SAM) to segment images without prompting by exploiting similarities in microscopy images, enabling zero-shot mask propagation similar to video.

0 favorites 0 likes
#image-segmentation

@lillyguisnet: WEEE!!! I had not had the opportunity to try SAM3.1 yet, but simply prompting for "worm" perfectly segmented my images!…

X AI KOLs Following ↗ · 2026-05-06 Cached

A user shares enthusiastic feedback about SAM 3.1's ability to accurately segment images using simple text prompts like 'worm', highlighting significant improvements over SAM 1.

0 favorites 0 likes
#image-segmentation

SAM 3: Segment Anything with Concepts

Papers with Code Trending ↗ · 2025-11-20 Cached

SAM 3 introduces a unified model for promptable concept segmentation and tracking, achieving state-of-the-art performance with a decoupled recognition and localization architecture and a scalable data engine.

0 favorites 0 likes
#image-segmentation

men1scus/birefnet

Replicate Explore ↗ · 2026-08-24 Cached

BiRefNet is an AI model for image segmentation available on Replicate, offering cost-effective inference on Nvidia A100 GPUs and is open-source.

0 favorites 0 likes
← Back to home

Submit Feedback