viewpoint-reproduction

Tag

Cards List
#viewpoint-reproduction

Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?

Hugging Face Daily Papers · 2026-05-31 Cached

Introduces Target Viewpoint Reproduction (TVR) task and TVRBench benchmark for evaluating foundation models' ability to actively adjust 3D viewpoints to match target images. Experiments reveal significant limitations in current open and closed-source models, with a unified post-training framework boosting success rates from ~12% to ~51%.

0 favorites 0 likes
← Back to home

Submit Feedback