works on
adaptive decoding 1long caption guidance 1monocular depth estimation 1robust depth prediction 1vision-language integration 1

From the 1 of 1 linked paper with an AI index.

collaborators

1 paper

cs.CV2026

Beyond Visual Ambiguity: Guiding Robust Monocular Depth Estimation in Challenging Scenarios via Detailed Long Captions

Junrui Zhang, Jiaqi Li, Yiran Wang +2

The paper introduces CapDepth, a framework that uses detailed long textual captions to guide monocular depth estimation, improving robustness on non‑Lambertian surfaces and in adve…