Author

Xin Lin

UCSD

h-index 12 Homepage View on Semantic Scholar

We have 1 of 22 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Preprint Aug 2026

PixelControl: Fine-Grained Condition Fidelity in Text-to-Image Diffusion

Experiments show that PixelControl improves structural fidelity and visual quality over existing controllable generation methods, with especially strong gains on boundaries and medium/small conditioned regions.

Xin Lin, Haodong Li, Zhifei Zhang et al. · 0 citations