Where to Look: Can Foundation Models Reach a Target Viewpoint Through Active Exploration?
Humans can reproduce the viewpoint specified by a target image through active head and body motion, yet spatial intelligence in foundation models has largely been studied as passive understanding of pre-collected observations. We introduce Target Viewpoint Reproduction (TVR) -- an active task where an agent adjusts its viewpoint in a 3D environment until its observation matches a given target image -- and TVRBench, an indoor-simulation benchmark spanning scene scale and target-view visual richness. TVR is far from solved: on the evaluation split, the strongest open-source and closed-source models reach only 7.8% and 12.0% success. Fine-grained analysis identifies two consistent bottleneck...
| Authors | Liyang Li, Muzhi Zhu, Zhiyue Zhao et al. |
|---|---|
| Primary category | cs.CV |
| Published | 31 May 2026 |
| Last updated at source | 31 May 2026 |
Models and datasets referencing this paper
- TVRBench/tvr-sft-vaDataset
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 17 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.