Getting it Right: Improving Spatial Consistency in Text-to-Image Models
| Autor: | Chatterjee, Agneet, Stan, Gabriela Ben Melech, Aflalo, Estelle, Paul, Sayak, Ghosh, Dhruba, Gokhale, Tejas, Schmidt, Ludwig, Hajishirzi, Hannaneh, Lal, Vasudev, Baral, Chitta, Yang, Yezhou |
|---|---|
| Rok vydání: | 2024 |
| Předmět: | |
| Druh dokumentu: | Working Paper |
| Popis: | One of the key shortcomings in current text-to-image (T2I) models is their inability to consistently generate images which faithfully follow the spatial relationships specified in the text prompt. In this paper, we offer a comprehensive investigation of this limitation, while also developing datasets and methods that support algorithmic solutions to improve spatial reasoning in T2I models. We find that spatial relationships are under-represented in the image descriptions found in current vision-language datasets. To alleviate this data bottleneck, we create SPRIGHT, the first spatially focused, large-scale dataset, by re-captioning 6 million images from 4 widely used vision datasets and through a 3-fold evaluation and analysis pipeline, show that SPRIGHT improves the proportion of spatial relationships in existing datasets. We show the efficacy of SPRIGHT data by showing that using only $\sim$0.25% of SPRIGHT results in a 22% improvement in generating spatially accurate images while also improving FID and CMMD scores. We also find that training on images containing a larger number of objects leads to substantial improvements in spatial consistency, including state-of-the-art results on T2I-CompBench with a spatial score of 0.2133, by fine-tuning on <500 images. Through a set of controlled experiments and ablations, we document additional findings that could support future work that seeks to understand factors that affect spatial consistency in text-to-image models. Comment: Accepted to ECCV 2024. Project Page : https://spright-t2i.github.io/ |
| Databáze: | arXiv |
| Externí odkaz: |
|