Get Started
Home
Topics
Search
Library
Research questionHow can monocular depth estimation remain accurate across adverse weather without harming clean-image performance?Fog, rain, snow, and low light alter image appearance in ways that can make monocular depth models misjudge scene geometry. Improving robustness to these conditions can also reduce performance on clean images.
AI
Computer Vision
Evaluation & Benchmarks
Image & Video Processing
Machine Learning
Research Paper
Technology
Latest papersRecent research connected to this question, newest first.Weather-Conditioned Depth AnythingThe source concerns Depth Anything-style monocular depth foundation models evaluated on curated weather benchmarks and standard clean benchmarks. It reports an average 3.7% AbsRel improvement on weather benchmarks while matching or slightly improving clean-benchmark performance; no deployment or sensor requirements are specified.research paper · Sep 4, 2026
Related questions
How can self-supervised monocular depth estimation stay accurate across scales and dynamic traffic on automotive edge devices?How can image restoration remove varied weather degradations from high-resolution images under tight compute budgets?How can RGB-D salient-object detection remain reliable when depth measurements are missing or corrupted?How can single-image depth estimation resolve scale ambiguity to produce consistent metric depth across environments?