DREAM: Diffusion Rectification and Estimation-Adaptive Models
We present DREAM, a novel training framework representing Diffusion Rectification and Estimation Adaptive Models, requiring minimal code changes (just three lines) yet significantly enhancing the alignment of training with sampling in diffusion models. DREAM features two components: diffusion rectification, which adjusts training to reflect the sampling process, and estimation adaptation, which balances perception against distortion. When applied to image super-resolution (SR), DREAM adeptly navigates the tradeoff between minimizing distortion and preserving high image quality. Experiments demonstrate DREAM's superiority over standard diffusion-based SR methods, showing a $2$ to $3\times $ faster training convergence and a $10$ to $20\times$ reduction in sampling steps to achieve comparable results. We hope DREAM will inspire a rethinking of diffusion model training paradigms.
Code (1)
Tasks
Image Super-ResolutionSuper-ResolutionMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
StableMotion: Repurposing Diffusion-Based Image Priors for Motion Estimation
We present StableMotion, a novel framework leverages knowledge (geometry and content priors) from pretrained large-scale image diffusion models to perform motion estimation, solving single-image-based image rectification…
Motion EstimationRolling Shutter CorrectionDream 7B: Diffusion Large Language Models
We introduce Dream 7B, the most powerful open diffusion large language model to date. Unlike autoregressive (AR) models that generate tokens sequentially, Dream 7B employs discrete diffusion modeling to refine sequences …
TARO: Temporal Adversarial Rectification Optimization Using Diffusion Models as Purifiers
Adversarial purification with diffusion models seeks to project adversarial examples back toward the data manifold, but balancing semantic preservation and robustness against adaptive attacks remains challenging. Recent …
Beyond Confidence: Adaptive and Coherent Decoding for Diffusion Language Models
Diffusion Language Models (DLMs) have recently achieved significant success due to their any-order generation capabilities. However, existing inference methods typically rely on local, immediate-step metrics such as conf…
Dream-Coder 7B: An Open Diffusion Language Model for Code
We present Dream-Coder 7B, an open-source discrete diffusion language model for code generation that exhibits emergent any-order generation capabilities. Unlike traditional autoregressive (AR) models that decode strictly…
Reinforcement LearningCode Generation