Low-Light Images

Follow this topic Ask about this topic

Momentum

0 papers in the last four weeks, down 100% on the four weeks before. 0.0% of all new papers.

Jul 13Week of Sep 28

Latest papers 29

All topics

OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes
Aug 30, 2026Muxin Liu, Tianbo Liu, Jing Xia +7Monocular Depth Estimation Robust Geometric Model Estimation
1The University of Hong Kong · 2Voyager Research, DiDi Chuxing · 3Southern University of Science and Technology
NTIRE 2026 Low-light Enhancement: Twilight Cowboy Challenge
Aug 10, 2026Aleksei Khalin, Egor Ershov, Artyom Panshin +46Low-Light Images Low-Light Image Enhancement
Deep Learning based Detection of Fishing Vessels and Fishing Monitoring using Nightlight Images
Aug 10, 2026Shantakar Mohanty, Prasun Kumar Gupta, Raian Vargas MarettoShip Detection Coral
Indian Institute of Remote Sensing, ISRO, Dehradun, India · University of Twente, Faculty of Geo-Information Science and Earth Observation (ITC), Enschede, The Netherlands
Toward Robust and 3D-Aware RGB-NIR Imaging in the Dark
Jul 31, 2026Muyao Niu, Mingze Ma, Yifan Zhan +5Low-Light Images Infrared
The University of Tokyo Tokyo, Japan · Adelaide University Adelaide, Australia · School of Artificial Intelligence (SAI) Shanghai Jiao Tong University Shanghai, China +1
Low-light Image Enhancement via Multi-scale Attention combined with Fourier Transform
Jul 27, 2026Wenbin Du, Jian Long, Zhu CaoLow-Light Image Enhancement Low-Light Images
aKey Laboratory of Smart Manufacturing in Energy Chemical Process, Ministry of Education, East China University of Science and Technology, Shanghai, 200237, China · bCollege of Electronics and Information Engineering, Tongji University, Shanghai 201804, China · cShanghai Research Institute for Intelligent Autonomous Systems, Tongji University, Shanghai 201210, China
SLAM in Low-Light Environments: Project Report
Jul 20, 2026Oleh Basystyi, Anna Stasyshyn, Oleksandr Kosovan +1Orb-Slam2 Simultaneous Localization And Mapping
Applied Sciences Faculty, Ukrainian Catholic University
WREN: Low Light Image Enhancement Using Retinex theory-based Double U-Net-like Structures
Jul 17, 2026Reina Kaneko, Junya Hara, Hiroshi Higashi +1Retinex Theory Low-Light Image Enhancement
The University of Osaka, Osaka, Japan · Kansai University, Osaka, Japan
FreeLit: Paired-Free Indoor Relighting via Physics-Guided Diffusion
Jul 15, 2026Chi-En Yen, Duy-Khanh Ngo, Wen-Wei Tang +3Image Relighting Low-Light Images
National Yang Ming Chiao Tung University
Event-RGB Adaptive Tracking for Nighttime Highway Perception
Jul 13, 2026Haidong Wang, Hengxing Cai, Wanlei Li +2Rgb-Event Object Tracking Multi-Object Tracking
School of Intelligent Systems Engineering, Sun Yat-sen University, Shenzhen, China · School of Intelligence Science and Engineering, Harbin Institute of Technology, Shenzhen, China
Why Low-Light Cameras Go Color Blind: Removing Color Bias in Raw Denoising
Jul 13, 2026Mohammad Mohammadi, Sina Honari, Stavros Tsogkas +6Low-Light Images Iterative Denoising Methods
University of Toronto · 2Vector Institute · 3AI-Center Toronto, Samsung +1
LUMINA-26: Low-Light Understanding for Modeling and Interpreting Night-time Actions
Jun 22, 2026Aman Kumar Pandey, Anil Singh PariharLow-Light Images Open-Vocabulary Action Recognition
Department of Computer Science and Engineering, Delhi Technological University, Delhi, India · Department of Computer Science, Delhi College of Arts and Commerce, University of Delhi, Delhi, India
AdaFuse-Det: Adaptive Cross-Modal Fusion of Event Cameras for Robust Object Detection in Low-Light RGB Imagery
May 23, 2026Raju Imandi, Chethana B, Bharatesh Chakravarthi +3Adaptive Feature Fusion Rgb-Event Object Tracking
SRM University AP, India · Aptiv, Bengaluru, India · Arizona State University, USA +2
Physen-Noise2Noise: Physics-Guided Self-Supervised Defocus Deblurring with Bias Correction under Low-Light Conditions
May 23, 2026Ziyan Huang, Lang Wu, Hongji Wang +3Gaussian Deblurring Low-Light Images
School of Mathematics and Statistics, Central South University, Changsha, 410083, People’s Republic of China · Key Laboratory for Micro/Nano Optoelectronic Devices of Ministry of Education, Hunan Provincial Key Laboratory of Low-Dimensional Structural Physics and Devices, School of Physics and Electronics, Hunan University, Changsha 410082, People’s Republic of China
PixIE: Prompted Pixel-Space Low-Light Image Enhancement
May 22, 2026Ruirui Lin, Guoxi Huang, David Bull +1Low-Light Image Enhancement Low-Light Images
Visual Information Laboratory, University of Bristol, United Kingdom
DarkShake-DVS: Event-based Human Action Recognition under Low-light andShaking Camera Conditions
May 20, 2026Jiaqi Chen, Qinfu Xu, Liyuan PanLow-Light Images 6-Dof
Beijing Institute of Technology
IG-Diff: Complex Night Scene Restoration with Illumination-Guided Diffusion Model
May 14, 2026Yifan Chen, Fei Yin, Chunle Guo +2Low-Light Images Image Restoration
Tsinghua Univerisity · NanKai University
Measurement-Adapted Eigentask Representations for Photon-Limited Optical Readout
May 11, 2026Tianyang Chen, Mandar M. Sohoni, Saeed A. Khan +5Low-Light Images Readout
Department of Electrical and Computer Engineering, Princeton University, Princeton, NJ 08544, USA · School of Applied and Engineering Physics, Cornell University, Ithaca, NY 14853, USA · USRA Research Institute for Advanced Computer Science, Mountain View, CA 94035, USA +1
SIMI: Self-information Mining Network for Low-light Image Enhancement
May 8, 2026Xuanshuo Fu, Lei Kang, Javier Vazquez-CorralLow-Light Image Enhancement Low-Light Images
Computer Vision Center, Barcelona, Spain · Computer Science Dept., Universitat Aut`onoma de Barcelona, Barcelona, Spain
AMIEOD: Adaptive Multi-Experts Image Enhancement for Object Detection in Low-Illumination Scenes
May 7, 2026Xiaochen Huang, Honggang Chen, Weicheng Zhang +4Low-Light Images Image Enhancement
College of Electronics and Information Engineering, Sichuan University, Chengdu 610065, China · Police Integration Computing Key Laboratory of Sichuan Province, China
BFORE: Butterfly-Firefly Optimized Retinex Enhancement for Low-Light Image Quality Improvement
May 5, 2026Ahmed CherifRetinex Theory Low-Light Image Enhancement
Sofrecom Tunisia, Orange Innovation, Tunis, 1053, Tunisia.
NTIRE 2026 Challenge on Efficient Low Light Image Enhancement: Methods and Results
May 4, 2026Jiebin Yan, Chenyu Tu, Weixia Zhang +8Low-Light Image Enhancement Low-Light Images
Beyond Pixel Fidelity: Minimizing Perceptual Distortion and Color Bias in Night Photography Rendering
Apr 30, 2026Furkan KınlıLow-Light Images Neural Radiance Fields
Bahc¸es¸ehir University Department of Artificial Intelligence Engineering ˙Istanbul, Türkiye
Learning Illumination Control in Diffusion Models
Apr 27, 2026Nishit Anand, Manan Suri, Christopher Metzler +2Illumination Variations Diffusion Models
University of Maryland College Park
Reading in the Dark: Low-light Scene Text Recognition
Apr 26, 2026Xuanshuo Fu, Lei Kang, Ernest Valveny +2Low-Light Images Scene Text Recognition
Computer Vision Center, Barcelona, Spain
BVI-Mamba: Video Enhancement Using a Visual State-Space Model for Low-Light and Underwater Environments
Apr 26, 2026Guoxi Huang, Ruirui Lin, Yini Li +2Underwater Image Enhancement Methods Vision State Space Models
Visual Information Laboratory, University of Bristol, Bristol, UK
Building Extraction from Remote Sensing Imagery under Hazy and Low-light Conditions: Benchmark and Baseline
Apr 16, 2026Feifei Sang, Wei Lu, Hongruixuan Chen +2Single Image Dehazing Remote Sensing
MOE Key Lab of ICSP, Anhui Provincial Key Lab of Multimodal Cognitive Computation, IMIS Lab of Anhui Province, School of Computer Science and Technology, Anhui University, Hefei, China · Graduate School of Frontier Sciences, The University of Tokyo, Chiba, 277-8561, Japan
PASDiff: Physics-Aware Semantic Guidance for Joint Real-World Low-Light Face Enhancement and Restoration
Mar 26, 2026Yilin Ni, Wenjie Li, Zhengxue Wang +3Low-Light Image Enhancement Low-Light Images
College of Automation, Nanjing University of Posts and Telecommunications, Nanjing, China · School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, China · PCA Lab, School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China +1
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
RL-AWB: Deep Reinforcement Learning for Auto White Balance Correction in Low-Light Night-time Scenes
Jan 8, 2026Yuan-Kang Lee, Kuan-Lin Chen, Chia-Che Chang +1Low-Light Images Scene Understanding
MediaTek Inc., Taiwan · National Taiwan University, Taiwan · National Yang Ming Chiao Tung University, Taiwan

Aug 30, 2026, cs.CVJ/K move · Enter open · S save

OptiGeo: Efficient Monocular Geometry for Embodied Perception in Optically Challenging Scenes

Muxin Liu, Tianbo Liu, Jing Xia, Xiaoyang Lyu+6

1The University of Hong Kong · 2Voyager Research, DiDi Chuxing · 3Southern University of Science and Technology

Monocular Depth Estimation Robust Geometric Model Estimation Geogs-Slam Perception Low-Light Images

Open paper AskPDF arXiv

Monocular depth estimation has achieved strong open-domain generalization, yet reliable robotic deployment remains difficult in transparent, reflective, and specular environments, where depth sensors often produce missing or biased depth. Existing methods often handle such optical failures with scene-specific preprocessing, auxiliary modules, or post-hoc fine-tuning. While effective in constrained settings, these designs increase architectural redundancy and can over-specialize general geometry models to narrow optical scenarios. We revisit this problem as a localized failure mode within base-model training and identify sensor-induced supervision bias as a key bottleneck: models inherit sensor failure patterns from biased real-depth supervision in optically challenging regions. We then introduce OptiGeo, a bias-aware training framework that rehabilitates biased real supervision using a clean-geometry teacher and residual-trimmed alignment. We redefine transparency-targeted rendering as a compact source of clean optical geometry, rather than a large domain-specific fine-tuning set. With only a small targeted rendering set, OptiGeo learns the geometric structure of transparent objects and regions, correcting local geometry distortions that real sensors cannot reliably supervise. Despite only 30M parameters, OptiGeo outperforms substantially larger 300M-scale monocular models and billion-scale multi-view baselines on transparent-scene benchmarks, while remaining competitive on general zero-shot depth and boundary sharpness. Real-world navigation cases further validate its practicality as an efficient perception module in optically challenging scenes.

Momentum

Related topics

Latest papers 29