Feature Recovery for Object Understanding After Irreversible Fire Damage
TRACE benchmark with 21.4K scenes studies post-fire object understanding; a Feature Recovery Module improves degraded-image retrieval by 12.5% and material recovery by 20.1%.
The paper introduces TRACE, a transformation-aware benchmark with 21.4K real-image-grounded synthetic scenes, 499 object identities across 189 categories, and five tasks covering degraded-object detection, pristine-state recovery, material recovery, description generation, and functional reasoning. Existing models degrade sharply: RF-DETR mAP falls 71% relative from least to most severe level, and InternVL3.5 retrieval R@1 drops from 93.85 to 28.11. The proposed Feature Recovery Module maps degraded encoder features to pristine-aligned representations while keeping the host model frozen, averaging relative gains of 12.5% for retrieval and 20.1% for material recovery across VLM hosts and severity levels.
- TRACE spans 21.4K scenes, 499 object identities, 189 categories, five tasks
- RF-DETR mAP drops 71% relative; InternVL3.5 retrieval R@1 falls from 93.85 to 28.11
- Feature Recovery Module is plug-and-play and keeps the host model frozen
- Average gains: 12.5% retrieval, 20.1% material recovery, larger under severe degradation
From the original article
1 min read at huggingface.co
Objects in post-fire environments often undergo irreversible physical transformations that change their geometry, material state, and visual appearance. Detecting and identifying these remnants is critical for locating hazards, reconstructing pre-incident contents, and inventorying losses. Unlike standard image corruptions, these degradations affect the physical structure of the object itself.
By Aditi Tiwari, Sofia Stoica, Savya Khosla · huggingface.co
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.