FreeTransformSR is a lightweight image super‑resolution network that uses a channel‑wise free low‑rank learnable transform to adaptively modulate features with minimal parameters. It adds a local feature modulation branch with depthwise convolution and a soft complexity adaptive module that fuses local convolution and window self‑attention based on texture characteristics. The model also employs an adaptive intensity modulation strategy and achieves competitive PSNR/SSIM on five benchmark datasets while using only 595K parameters and running faster than competing methods.
By Hongji Li, Yunhui Li
arXiv:2606.15158v3 Announce Type: replace
Abstract: Reference-guided generation (e.g., object compositing, customization) has progressed rapidly, yet current pipelines share a fundamental limitation:...
By Jeahun Sung, Dahyeon Kye, Soo Ye Kim, Jihyong Oh
arXiv:2608.30782v1 Announce Type: new
Abstract: Real-world image super-resolution (Real-ISR) aims to preserve structures supported by the degraded observation while reconstructing perceptually realis...
By Bingtian Qiao, Yue Shi, Yong Guo, Wenjun Zhang, Jiezhang Cao
arXiv:2609.16578v1 Announce Type: new
Abstract: The spatial support required for image restoration varies across degradation types, image regions, and reconstruction stages. However, most existing me...
By Hu Gao, Lizhuang Ma, Yulong Chen
arXiv:2406. 07435v2 Announce Type: replace-cross Abstract: Image restoration networks are usually comprised of an encoder and a decoder, responsible for aggregating image content from noisy, distorted data and to restore clean, undistorted images, respectively.
By Shashank Agnihotri, Julia Grabinski, Janis Keuper, Margret Keuper
Incorrect exposure degrades both image brightness and recoverable scene detail. Existing sRGB-based correction methods are limited by the non-linear image signal processing pipeline, whereas RAW-based...
Remote sensing images acquired by unmanned aerial vehicles (UAVs) and satellites are often degraded by adverse weather, illumination variation, and imaging artifacts, which may co-occur and jointly induce global distribution shifts and local structural corruption. Although All-in-One image restoration offers an appealing unified alternative to task-specific pipelines, existing methods still suffer from weak or implicit degradation cues and parameter redundancy caused by full-rank multi-expert designs with overlapping restoration behaviors.
arXiv:2609.13791v1 Announce Type: new
Abstract: Recognition pipelines typically adopt a restore-then-recognize workflow, yet decades of experience show that generating visually pleasing images seldom...
By Lanqing Guo, Xijun Wang, Minchul Kim, Yu Yuan, Wes Robbins, Xingguang Zhang, Nicholas Chimitt, Stanley H. Chan, Zhangyang Wang, Xiaoming Liu
The paper introduces DLC, a metric-guided dynamic loss controller that adjusts the weighting of existing training losses during multi-objective image restoration. DLC evaluates the model on a fixed feedback subset and uses quality metrics to update the loss-weight vector via an LLM-based controller, without altering the restoration architecture or adding new loss terms. Experiments on low-light enhancement, deraining, and super-resolution demonstrate that DLC guides training toward balanced fidelity and perceptual quality across diverse domains.
By Jaewan Ko, Janghoon Choi
The paper introduces SPARK, a lightweight input‑conditioned controller that modulates only a few dominant channels in frozen Diffusion Transformer (DiT) based super‑resolution models. By predicting bounded per‑channel affine transformations for selected channels, SPARK improves reconstruction fidelity and perceptual quality without fine‑tuning the backbone or adding adapters. Experiments on three DiT‑based SR backbones across DIV2K, RealSR, and DRealSR demonstrate consistent gains while modulating only eight channels per stream and block.
By Federico Putamorsi, Leonardo Zini, Marcella Cornia, Lorenzo Baraldi
The paper introduces SANA‑SR, an efficient one‑step diffusion restoration framework for real‑world image super‑resolution. It uses a deep compression autoencoder to reduce latent tokens by a 32× ratio, preserving essential structures and textures, and applies a linear‑attention DiT with LoRA fine‑tuning for linear‑complexity token mixing. Experiments show competitive or superior performance on benchmark datasets, and the pruned model runs in 0.019 s with 407.95 G MACs and 344 M parameters, indicating strong potential for mobile deployment.
By Bingtian Qiao, Yue Shi, Yingjie Zhou, Yong Guo, Guangtao Zhai, Jiezhang Cao
arXiv:2609.31170v1 Announce Type: new
Abstract: Task-driven image restoration aims to improve both image quality and downstream task performance. However, existing methods predominantly focus on sing...
By Yanjie Tu, Qingsen Yan, Axi Niu, Wenxuan Cai, Tao Hu, Wei Dong, Haokui Zhang