Can Text-to-Image Models Draw from the Right Frame of Reference?
Spatial instruction following has become a crucial requirement for text-to-image (T2I) generation. A common challenge arises when directional expressions are interpreted under different frames of reference. For example, ``the left of'' may refer to the viewer's image coordinates or to the intrinsic orientation of an object, leading to different expected layouts. Existing T2I benchmarks reveal important layout failures, yet they rarely isolate whether models can follow a specified frame of reference when it differs from camera view. To mitigate this gap, we introduce FoR-T2I, a benchmark for evaluating this distinction with 1,200 prompt pairs built from controlled spatial layouts. In each ...
| Authors | Zheyuan Gu, Ruihang Li, Yong Huang et al. |
|---|---|
| Primary category | cs.CV |
| Published | 4 August 2026 |
| Last updated at source | 4 August 2026 |
Connected in the knowledge graph
- ernie-research/FoR-T2IDataset · cited by
Models and datasets referencing this paper
- ernie-research/FoR-T2IDataset
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 Information may be incomplete or out of date.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.