Tootfinder

ReLumix: Extending Image Relighting to Video via Video Diffusion Models
Lezhong Wang, Shutong Jin, Ruiqi Cui, Anders Bjorholm Dahl, Jeppe Revall Frisvad, Siavash Bigdeli
https://arxiv.org/abs/2509.23769

ReLumix: Extending Image Relighting to Video via Video Diffusion Models
Controlling illumination during video post-production is a crucial yet elusive goal in computational photography. Existing methods often lack flexibility, restricting users to certain relighting models. This paper introduces ReLumix, a novel framework that decouples the relighting algorithm from temporal synthesis, thereby enabling any image relighting technique to be seamlessly applied to video. Our approach reformulates video relighting into a simple yet effective two-stage process: (1) an ar…

CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy
Cunmin Zhao, Ziyuan Luo, Guoye Guan, Zelin Li, Yiming Ma, Zhongying Zhao, Renjie Wan
https://arxiv.org/abs/2508.19300

CellINR: Implicitly Overcoming Photo-induced Artifacts in 4D Live Fluorescence Microscopy
4D live fluorescence microscopy is often compromised by prolonged high intensity illumination which induces photobleaching and phototoxic effects that generate photo-induced artifacts and severely impair image continuity and detail recovery. To address this challenge, we propose the CellINR framework, a case-specific optimization approach based on implicit neural representation. The method employs blind convolution and structure amplification strategies to map 3D spatial coordinates into the hi…

I set my watch to notify on zone 2 borders and “ran” 🙄 for an hour. Early on, it felt like I was constantly roofing it, but as I got deeper into it, everything seemed to settle. I’m going to try to stay with it, but I don’t know if I can intentionally go so slowly for weeks and weeks.
Saw my fox buddy on the drive home.
#Running

That's how our hike at the #mummelsee started ... and how it was when we were up there. - But the walk was quite okay.
We checked the rain radar and decided to go back down rather quickly. We leveraged our rain gear and it did not disappoint us! 🙂
So we didn't see the area atop - the so called

Fuzzy-Based Control Method for Autonomous Spacecraft Inspection with Minimal Fuel Consumption
Daegyun Choi, Donghoon Kim, Henzeh Leeghim
https://arxiv.org/abs/2508.18583 https:/…

Fuzzy-Based Control Method for Autonomous Spacecraft Inspection with Minimal Fuel Consumption
This study explores an energy-efficient control strategy for spacecraft inspection using a fuzzy inference system combined with a bio-inspired optimization technique to incorporate learning capability into the control process. The optimized fuzzy controller produces a minimally fuel-consuming force while maintaining reliable inspection within constraints, such as illumination, restricted field of view, thrust limits, and safe regions. The performance of the proposed control strategy is validate…

From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Guoxi Huang, Haoran Wang, Zipeng Qi, Wenjun Lu, David Bull, Nantheera Anantrasirichai
https://arxiv.org/abs/2509.17789

From Restoration to Reconstruction: Rethinking 3D Gaussian Splatting for Underwater Scenes
Underwater image degradation poses significant challenges for 3D reconstruction, where simplified physical models often fail in complex scenes. We propose \textbf{R-Splatting}, a unified framework that bridges underwater image restoration (UIR) with 3D Gaussian Splatting (3DGS) to improve both rendering quality and geometric fidelity. Our method integrates multiple enhanced views produced by diverse UIR models into a single reconstruction pipeline. During inference, a lightweight illumination g…

Good morning from Harlem
#Photography #GoodMorning #Sunrise #NYC

Do Natural Language Descriptions of Model Activations Convey Privileged Information?
Millicent Li, Alberto Mario Ceballos Arroyo, Giordano Rogers, Naomi Saphra, Byron C. Wallace
https://arxiv.org/abs/2509.13316

Do Natural Language Descriptions of Model Activations Convey Privileged Information?
Recent interpretability methods have proposed to translate LLM internal representations into natural language descriptions using a second verbalizer LLM. This is intended to illuminate how the target model represents and operates on inputs. But do such activation verbalization approaches actually provide privileged knowledge about the internal workings of the target model, or do they merely convey information about its inputs? We critically evaluate popular verbalization methods across datasets…

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
Tianyue Wang, Shuang Yang, Shiguang Shan, Xilin Chen
https://arxiv.org/abs/2509.16031 …

GLip: A Global-Local Integrated Progressive Framework for Robust Visual Speech Recognition
Visual speech recognition (VSR), also known as lip reading, is the task of recognizing speech from silent video. Despite significant advancements in VSR over recent decades, most existing methods pay limited attention to real-world visual challenges such as illumination variations, occlusions, blurring, and pose changes. To address these challenges, we propose GLip, a Global-Local Integrated Progressive framework designed for robust VSR. GLip is built upon two key insights: (i) learning an init…

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
Luyang Cao, Han Xu, Jian Zhang, Lei Qi, Jiayi Ma, Yinghuan Shi, Yang Gao
https://arxiv.org/abs/2508.09009

Towards Perfection: Building Inter-component Mutual Correction for Retinex-based Low-light Image Enhancement
In low-light image enhancement, Retinex-based deep learning methods have garnered significant attention due to their exceptional interpretability. These methods decompose images into mutually independent illumination and reflectance components, allows each component to be enhanced separately. In fact, achieving perfect decomposition of illumination and reflectance components proves to be quite challenging, with some residuals still existing after decomposition. In this paper, we formally name t…