T2I-CompBench: A Comprehensive Benchmark for Open-world Compositional Text-to-image Generation

By Kaiyi Huang, Kaiyue Sun, Enze Xie, Zhenguo Li, Xihui Liu. Neural Information Processing Systems, 2023

375 citations recorded by the source corpus.

,

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/f5945b1421ee8e0cd59e674b73f4ad82a71f66c7

Citations in the corpus

• Flow-GRPO: Training Flow Matching Models via Online RL (2025, neutral): “However, they often struggle with composing complex scenes involving multiple objects, attributes, and relationships [6, 7], as well as text rendering [8].”