Reproduce “MeteoVerse: Unified Weather-Controllable Video World Model” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Renlong Wu, Guanqiao Wang, Xuan Shang, Yin Hanming, Xiaoxiao Sheng, Tianyu Huang, Hui Li, Wangmeng Zuo
MeteoVerse generates camera-controlled future videos from one image while explicitly modeling weather changes. It predicts the input and target rain, snow, and fog states, then uses their differences to guide category-specific weather experts; scene descriptions and camera paths separately guide scene and viewpoint. On 400 held-out cases, Weather Alignment for weather introduction was 61.00, versus 29.00 for VerseCrafter, on the benchmark.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.