The Flow has not summarised this story yet — read it at arXiv Computer Vision.
arXiv:2606. 04299v1 Announce Type: cross Abstract: We consider the problem of generating images whose internal structure -- defined by the distribution of patches across multiple scales -- matches that of a single reference image.
The paper introduces a tensor‑based functional for targeted image enhancement and denoising, incorporating application‑dependent and contextual information through explicit regularization. It establishes existence of a minimizer and discusses tensor symmetry constraints, convexity, and geometric interpretation. The framework demonstrates strong performance in nonlinear scenarios like gamma correction and targeted value‑range filtering, achieving results comparable to state‑of‑the‑art PDE‑based methods.
The paper explores using denoising diffusion generative models as plug‑and‑play priors for high‑dimensional inference problems. By combining a pre‑trained diffusion prior with a differentiable auxiliary constraint, the authors enable approximate inference through iterative differentiation across multiple noisy versions of the data. This framework opens possibilities for conditional generation, image segmentation, and novel combinatorial optimization algorithms.
arXiv:2608.29227v1 Announce Type: new Abstract: In this work we propose a novel non-linear diffusion filtering approach for images based on their channel representation. To derive the diffusion updat...
arXiv:2608. 14706v1 Announce Type: cross Abstract: Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data.
arXiv:2609.37529v1 Announce Type: cross Abstract: Pretrained denoisers provide a powerful way to incorporate image priors into restoration algorithms. Plug-and-Play and RED approaches exploit fixed-n...