8 papers
Spatial Gram Alignment for Ultra-High-Resolution Image Synthesis
Jinjin Zhang, Xiefan Guo, Di Huang
Modern ultra-high-resolution image synthesis relies heavily on the robust generative capacity of large-scale pre-trained Latent Diffusion Models (LDMs). While recent representation…
What Makes Synthetic Data Effective in Image Segmentation
Jinjin Zhang, Xiefan Guo, Yizhou Jin +2
Driven by rapid advances in large-scale generative models, synthetic data has emerged as a promising solution for visual understanding. While modern diffusion models achieve remark…
EruDiff: Refactoring Knowledge in Diffusion Models for Advanced Text-to-Image Synthesis
Xiefan Guo, Xinzhu Ma, Haoxiang Ma +2
Text-to-image diffusion models have achieved remarkable fidelity in synthesizing images from explicit text prompts, yet exhibit a critical deficiency in processing implicit prompts…
CTCal: Rethinking Text-to-Image Diffusion Models via Cross-Timestep Self-Calibration
Xiefan Guo, Xinzhu Ma, Haiyu Zhang +1
Recent advancements in text-to-image synthesis have been largely propelled by diffusion-based models, yet achieving precise alignment between text prompts and generated images rema…
ShortFT: Diffusion Model Alignment via Shortcut-based Fine-Tuning
Xiefan Guo, Miaomiao Cui, Liefeng Bo +1
Backpropagation-based approaches aim to align diffusion models with reward functions through end-to-end backpropagation of the reward gradient within the denoising chain, offering…
Ultra-High-Resolution Image Synthesis: Data, Method and Evaluation
Jinjin Zhang, Qiuyu Huang, Junjie Liu +2
Ultra-high-resolution image synthesis holds significant potential, yet remains an underexplored challenge due to the absence of standardized benchmarks and computational constraint…