← Back to all news
arXiv Computer Vision By Imane Si Salah, Emile Cribelier, Thomas Veit, Wolf Hauser, Arthur Leclaire

Controllable blind deblurring with diffusion models

Read the original on arXiv Computer Vision →

The paper introduces SuperSharpen, a diffusion-based method for blind deblurring in professional photography that can invert unknown isotropic blur without knowing the degradation kernel. It offers explicit control over restoration strength via a blur measure and compares two conditioning strategies: a ControlNet-style adapter on a frozen backbone and full finetuning of the diffusion prior. Experiments on synthetic and real-world blur show that finetuning yields higher fidelity with fewer hallucinated details, improving perceptual quality and controllable restoration strength.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Computer Vision.

Related stories

arXiv AI
Jul 24

RealVDeblur: One-Step Diffusion for Generalizable Real-World Video Deblurring

arXiv:2607. 20628v1 Announce Type: cross Abstract: Real-world video deblurring remains challenging due to diverse motion patterns, complex degradations, and the scarcity of realistic training data, yet robust restoration is critical for downstream pipelines such as mobile imaging and 3D reconstruction.

By Renbiao Jin, Mingxin Yang, Yutian Chen, Junhao Zhuang, Xin Cai, Mulin Yu, Linning Xu, Wenxian Yu, Danping Zou, Shi Guo, Tianfan Xue
diffusionbenchmarks
More like this →
arXiv AI
Oct 2

PickMoment: Continuous-Time Single-Image-to-Video via Learning Deblurring and Blur-to-Video

PickMoment is a continuous‑time model that learns to predict the interval‑mean blur over arbitrary sub‑intervals of a camera exposure, unifying single‑image deblurring, blur‑to‑video generation, and continuous‑time pick‑a‑moment recovery. It is trained with three supervisions derived from the blur integral: an empirical reconstruction loss, an additivity loss for self‑consistency, and a sharp‑frame loss at zero interval. The model achieves state‑of‑the‑art performance on GoPro and HIDE for generative deblurring, competitive results on RealBlur, and the highest per‑frame fidelity on GoPro‑7 blur‑to‑video, all in a single forward pass.

By Junseong Shin, Hyeonsu Jo, Daehyun Kim, Tae Hyun Kim
diffusionbenchmarks
More like this →
arXiv Computer Vision
Oct 12

UniDeblur: Unified Motion Deblurring via Fourier Convolution Learning

UniDeblur introduces a unified motion deblurring framework that learns blur-adaptive global filters in Fourier space, addressing the limitations of pixel-level mapping in existing methods. By constructing a multi-source dataset and implementing a data pruning and quality control pipeline, the model can handle diverse motion blur kernels across different cameras and image contents. Experiments show that UniDeblur performs competitively on both in-domain and out-of-domain benchmarks, demonstrating its effectiveness for varied blur scenarios.

By Xintian Mao, Jiansheng Wang, Huaiyuan Wang, Qingli Li, Yan Wang
computer-visionefficiencybenchmarks
More like this →
arXiv Computer Vision
6d ago

Taming Noise Initialization for Zero-shot Video Restoration with Image Diffusion Priors

The paper introduces a method for zero‑shot video restoration that improves upon prior approaches by using DDIM inversion on corrupted video frames to generate noise that preserves temporal correlations. An adaptive noise blending strategy is added to reduce degradation patterns while gradually moving toward Gaussian noise, and a measurement‑guided trajectory attention mechanism further enhances temporal consistency. Experiments on DAVIS, REDS4, and Set8 datasets show that this approach outperforms existing zero‑shot video restoration methods.

By Chong Wang, Zixuan Fu, Hao Cheng, Siyuan Yang, Alex C. Kot, Bihan Wen
diffusion
More like this →