Fog

Follow this topic Ask about this topic

Momentum

2 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 21

All topics

The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators
Sep 29, 2026Thomas Deixelberger, Markus SteinbergerDomain Adaptation Conditional Gans
Huawei, Austria · Graz University of Technology, Austria
GRADE: Single-Frame Generative Radar Depth Estimation Under Visual Degradation
Sep 11, 2026Bin Zhao, Patrick Chiou, Nakul GargDepth Estimation Radar
Rice University
Enhancing Visual Perception in Foggy Conditions via Multiclass Fog Density Modeling
Aug 3, 2026Mohamad Mofeed Chaar, Galia WeidlFog Autonomous Driving Perception
Connected urban mobility, Faculty of Engineering, University of Applied Sciences, Aschaffenburg, Germany
FogDrive: A Multi-Modal Synthetic Driving Dataset for Perception under Graded Fog
Jul 18, 2026Vansh PanwarFog Naturalistic Driving Data
Indian Institute of Technology, Guwahati
fog: Expressing Motion and Emotion through Function Composition of AI-Generated Code
Jul 8, 2026Vivian Liu, Lydia ChiltonFog Motion
Columbia University New York, USA
A Task-Driven Evaluation of UAV Detection and Tracking under Synthetic Fog
Jul 6, 2026Amir Pouladi, Vesal Ahsani, Haijun Li +2Unmanned Aerial Vehicle Detection Fog
Center for Aerospace Research (CfAR), University of Victoria, Victoria, BC, Canada · Advanced Control and Intelligent Systems (ACIS) Lab, University of Victoria, Victoria, BC, Canada
From Fog Chamber to Aircraft Window: Pixel-Registered Imaging and Synthetic Fine-Tuning Enable Cross-Domain Defogging
Jun 27, 2026Alexander Ingold, Sabina D. Menon, Manya Yellepeddy +5Fog Single Image Dehazing
Department of Electrical and Computer Engineering, University of Utah, Salt Lake City, UT 84112, USA · U.S. Naval Research Laboratory Remote Sensing Division, Washington DC 20375, USA.
FoggyTrust: Robust Federated Learning with Hierarchical Trust Networks
Jun 26, 2026Emmanuel Rassou, Tomas GonzalezFederated Learning Log-Ratio-Based Gaussian Trust Weight
School of Engineering and Applied Sciences (SEAS) Harvard Cambridge, MA, USA
OnDeFog: Online Decision Transformer under Frame Dropping
Jun 18, 2026Daiki Yotsufuji, Kenta Nishihara, Shoma Shimizu +2Fog Frame Rate
Yokohama National University, Kanagawa, Japan
E2LLM: Towards Efficient LLM Serving in Heterogeneous Edge/Fog Environments
Jun 2, 2026Truong-Thanh Le, Amir Taherkordi, Hoang-Loc La +3LLM Inference Optimization Edge Devices
Department of Informatics University of Oslo Oslo, Norway · Department of Computer Science UiT The Arctic University of Norway Tromsø, Norway
Lost in Fog: Sensor Perturbations Expose Reasoning Fragility in Driving VLAs
May 20, 2026Abhinaw Priyadershi, Jelena FrtunikjFog Degradation
NVIDIA Corporation, USA · NVIDIA GmbH, Germany
Seeing Through Fog: Towards Fog-Invariant Action Recognition
May 20, 2026Enqi Liu, Liyuan Pan, Zhi Gao +2Open-Vocabulary Action Recognition Fog
Beijing Institute of Technology, Beijing, China · Beijing Institute for General Artificial Intelligence, Beijing, China · Yangtze Delta Region Academy of Beijing Institute of Technology, Jiaxing, China
D2-CDIG: Controlled Diffusion Remote Sensing Image Generation with Dual Priors of DEM and Cloud-Fog
May 14, 2026Zuopeng Zhao, Ying Liu, Kanyaphakphachsorn Pharksuwan +3Remote Sensing Digital Elevation Models
School of Computer Science and Technology/School of Artificial Intelligence, China University of Mining and Technology, Xuzhou 221116, China
Unifying Physically-Informed Weather Priors in A Single Model for Image Restoration Across Multiple Adverse Weather Conditions
May 13, 2026Jiaqi Xu, Xiaowei Hu, Lei Zhu +1Image Restoration Fog
Department of Computer Science and Engineering, The Chinese University of Hong Kong, Hong Kong SAR, China · Shanghai Artificial Intelligence Laboratory, Shanghai, China · ROAS Thrust, the Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China +1
A Data Efficiency Study of Synthetic Fog for Object Detection Using the Clear2Fog Pipeline
May 12, 2026Mohamed Ahmed Mohamed, Xiaowei HuangFog Synthetic-To-Real Domain Gap
School of Computer Science and Informatics, University of Liverpool, Liverpool, L69 3DR, UK
Ensuring Logic in the Fog: Sound POMDP Synthesis with LTL Objectives
May 12, 2026Can Zhou, Yulong Gao, Pian YuLinear Temporal Logics Partially Observable Markov Decision Process
Imperial College London, United Kingdom · University College London, United Kingdom
Optimizing Server Placement for Vertical Federated Learning in Dynamic Edge/Fog Networks
May 10, 2026Su Wang, Mung Chiang, H. Vincent PoorFederated Learning Fog
Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ, USA · Department of Electrical and Computer Engineering, Purdue University, West Lafayette, IN, USA
FieryGS: In-the-Wild Fire Synthesis with Physics-Integrated Gaussian Splatting
Apr 30, 2026Qianfan Shen, Ningxiao Tao, Qiyu Dai +6Combustion Control Dynamic 3D Gaussian Splatting
School of EECS, Peking University · School of Intelligence Science and Technology, Peking University · 3Yuanpei College, Peking University +3
Single Image Defogging Using a Fourth-Order Telegraph PDE Guided by Physical Haze Modeling
Apr 26, 2026Manish Kumar, Rajendra K. RaySingle Image Dehazing Image Restoration
School of Mathematical and Statistical Sciences, Indian Institute of Technology Mandi, Mandi (H.P), 175075, India
Physically-Induced Atmospheric Adversarial Perturbations: Enhancing Transferability and Robustness in Remote Sensing Image Classification
Apr 16, 2026Weiwei Zhuang, Wangze Xie, Qi Zhang +9Fog Remote Sensing
School of Computer and Information Engineering, Xiamen University of Technology, Xiamen, 361000, China · Faculty of Data Science, City University of Macau, Macau SAR, China · Dundee International Institute, Central South University, Changsha, China +7
RoboLight: A Dataset with Linearly Composable Illumination for Robotic Manipulation
Mar 4, 2026Shutong Jin, Jin Yang, Muhammad Zahid +1Large-Scale Robot Demonstration Datasets Robotic Manipulation
School of Electrical Engineering and Computer Science, KTH Royal Institute of Technology

Sep 29, 2026, cs.CVJ/K move · Enter open · S save

The Domain Is a Residue: Adapting Self-Supervised Features, Not Generators

Thomas Deixelberger, Markus Steinberger

Huawei, Austria · Graz University of Technology, Austria

Domain Adaptation Conditional Gans Fog Dino Bivariate Bicycle Codes

Open paper AskPDF arXiv

Clearing fog, rain or snow from footage, or turning renders into photographs, must remove the source domain and keep the scene. Unpaired translators carry it through because their generator sees the source appearance (pixels, a near-invertible latent or a control map) and keeps it. A DINO feature map fixes what is in the scene and carries weather, lighting and rendering style as a residue of 13 to 14% of the feature norm. We propose the Representation Feature Adapter (RFA), a 2.9M-parameter network that moves this residue. We train only the adapter and its discriminators; the encoder and a feature-conditioned decoder, trained once for all conditions, stay frozen. Against CycleGAN-Turbo it is ahead on both metrics on fog and on KID on night, and level within noise on snow, rain and haze. On sim-to-real it leads REGEN and HyPER-GAN on both metrics. Only the RFA removes the rain while keeping the scene. The removal costs scene structure: CycleGAN-Turbo keeps more on every condition but fog. On VAE latents the identical adapter collapses to the identity, and decoders from other groups that never saw it render its output. The RFA has about 160 times fewer trainable parameters than CycleGAN-Turbo and under a fifth of its per-condition training time.

Momentum

Related topics

Latest papers 21