Tag
This paper proposes Decoupled Residual Denoising Diffusion Models (DRDD) for unified and data-efficient image-to-image translation, decoupling noise diffusion for domain harmonization from residual diffusion for semantic mapping.
This paper introduces StableI2I, a reference-free evaluation framework for assessing content fidelity and consistency in image-to-image generation tasks. It also presents StableI2I-Bench, a benchmark for evaluating multi-modal language models on these assessment tasks.