This source only provides a headline — there is no body to show. Use “Read the original” below to read it at the source.
Learning What to Degrade: A Recoverability-Aware Curriculum for Reliable Smart-Glasses Super-Resolution
arXiv:2611.23674v1 Announce Type: new Abstract: Degradations in smart-glasses images obscure small text and fine-grained structures needed by vision-language models (VLMs) for visual assistance. We introduce an high-resolution (HR)-referenced semantic evaluation protocol that compares VLM outputs on restored images with those on corresponding HR references. Our evaluation reveals two failure modes: generative SR can synthesize misleading details, whereas restoration-oriented SR can leave critical evidence blurred or ambiguous. These findings motivate improving faithful detail recovery in restoration-oriented SR, where a key training challenge is to provide sufficiently difficult inputs while retaining recoverable visual information. We propose ReDiC (Recoverability-Difficulty Curriculum), which combines a model-independent recoverability proxy with model-relative restoration difficulty to adapt training degradation severity. ReDiC increases severity when inputs are recoverable and rest…