PREEN (Preset Regression via an Exemplar-based Editor Network) performs color style transfer by predicting a 29‑parameter preset for a deterministic image editor, rather than generating a raster image. It uses a style‑transfer teacher to create pseudo‑presets, then trains a CLIP‑conditioned regressor refined with LoRA and a CIELAB loss. On the PST50 benchmark, PREEN outperforms baselines in pixel‑ and perceptual‑fidelity, runs in sub‑second on‑device latency, and offers a single inference‑time strength knob that smoothly transitions from default to vivid presets.
By Beomjin Ahn
arXiv:2610.15806v2 Announce Type: replace
Abstract: Recovering visually faithful content from damaged video bitstreams is important for reliable multimedia communication and storage. Existing methods...
By Tianyi Liu, Jiaojiao Wang, Ye Lu, Kejun Wu, Chengtao Cai, Zhengguo Li, Chia-Wen Lin
arXiv:2509.24022v3 Announce Type: replace
Abstract: Image reconstruction from corrupted images is crucial across many domains. Most reconstruction networks are trained on post-ISP sRGB images, even t...
By Nate Rothschild, Moshe Kimhi, Avi Mendelson, Chaim Baskin
arXiv:2608.21847v1 Announce Type: new
Abstract: Low-light image enhancement (LLIE) must correct ambiguous exposure without overwriting structure already supported by the input. Generative transport c...
By Yi Ai, Zheng Chen, Yuanhao Cai, Yulun Zhang, Xiaokang Yang
arXiv:2610.34742v1 Announce Type: new
Abstract: Reconstructing 1-m imagery from Sentinel-2 combines two difficulties. The input and the reference are observed by different satellites, which differ in...
By Tailai Chen, Yuluxin Fu, Jie Deng, Shu Luo, Yanan Wu, Danfeng Hong
Paint-Anything introduces a unified hex-prompt interface that allows users to specify any 24‑bit hex color for both image generation and editing. The method trains on a new Paint‑500K dataset created from real images with object grounding, perceptual color labeling, and editing‑pair synthesis, and supplements this with pure‑color anchors to address shadow‑induced color inaccuracies. Evaluated on the newly proposed Any Color Benchmark (ACBench), Paint‑Anything achieves significant improvements over the base FLUX.2‑4B model, boosting T2I and editing scores by 85.3 % and 28.3 % respectively, and outperforms competing methods on the CompColor metric.
By Ji Xie, Dewei Zhou, Xinyu Huang, Zhennan Chen, Xun Wang
PolarScale is a new benchmark that explicitly requires models to predict the radiometric scale needed for full Stokes reconstruction from a per-scene normalized total‑intensity image. It evaluates models on normalized Stokes components, AoLP/DoLP/DoCP, and a per‑scene scale, using metrics that include angular, self‑consistency, and physical‑bound checks. Across seven restoration‑based and generative backbones, the best restoration models achieve a 3.6‑4.3% mean relative error in scale estimation, outperforming a constant‑scale control and maintaining physical plausibility.
By Beibei Lin, Tingting Chen, Xin Zhang, Wenhao Zhao, Dongjun Li, Zifeng Yuan
The paper benchmarks two strategies for blind image restoration around a fixed image signal processor (ISP): restoring in the RAW domain before the ISP (pre‑ISP) and restoring in the sRGB domain after the ISP (post‑ISP). Across four smartphone groups, two learned ISPs, and three degradation regimes (noise, blur, and combined noise‑blur), the study finds that RAW restoration generally outperforms generic RGB restoration, but RGB models trained with ISP‑aware supervision achieve the best overall performance. The authors emphasize that restoration performance depends heavily on how well the restoration model aligns with the imaging pipeline, and they recommend reporting restoration placement and ISP‑aware supervision as key experimental factors.
By Zihao Lu, Radu Timofte, Marcos V. Conde
arXiv:2610.09125v1 Announce Type: new
Abstract: Reference-based object compositing inserts or replaces an object using a background image, a reference image, and a 2D compositing mask. These inputs g...
By Sanghyun Jo, Chae Yeon Lim, Donghwan Lee, Sihyun Kim, Soo Ye Kim, Kyungsu Kim
arXiv:2607.22380v3 Announce Type: replace
Abstract: Infrared multi-frame super-resolution (MFSR) exploits complementary observations to recover spatial detail, but its evaluation remains fragmented a...
By Jie Deng, Heyang Wang, Changxin Wang, Junkai Shen, Hongyi Chen, Zhiping He, Hongxing Qi, Xudong Zhang, Jianyu Wang
EventSeeColor is a method that reconstructs color images from monochrome event camera data. It combines event‑reconstructed grayscale images with aligned events to guide a diffusion colorizer, using semantic context and region‑balanced chroma supervision to improve color fidelity. Evaluations on two real event datasets show that EventSeeColor outperforms existing methods in structural similarity, perceptual scores, and chromatic‑region color difference.
By Chuanzhi Xu, Langyi Chen, Haoxian Zhou, Zelin Zhang, Haodong Chen, Qiang Qu, Xiaoming Chen, Weidong Cai
Raw images inherently suffer from noise due to the stochastic nature of light and sensor hardware imperfections. As real photon counts fall, the ratio of this noise to the signal degrades; consequently, for low-light conditions, robust denoising is especially vital for high-quality results.