多模态信息融合

High Dynamic Range 3D Gaussian Splatting via Luminance-Chromaticity Decomposition

高动态范围3D高斯散射 via 光亮度-色度分解

Kaixuan Zhang, Minxian Li, Mingwu Ren, Jiankang Deng, Xiatian Zhu

机构 * Nanjing University of Science and Technology（南京理工大学） ； Imperial College London（伦敦帝国理工学院） ； University of Surrey（萨里大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出基于光亮度-色度分解的3D高斯散射方法，通过解耦亮度与色度参数，提升学习灵活性，实现更高效的高动态范围3D重建。

High-Speed Full-Color HDR Imaging via Unwrapping Modulo-Encoded Spike Streams

通过解调编码脉冲流实现高速全彩HDR成像

Chu Zhou, Siqi Yang, Kailong Zhang, Heng Guo, Zhaofei Yu, Boxin Shi, Imari Sato

机构 * Digital Content and Media Sciences Research Division, National Institute of Informatics（国家信息研究所数字内容与媒体科学研究中心） ； Pattern Recognition and Intelligent System Laboratory, School of Artificial Intelligence, Beijing University of Posts and Telecommunications（人工智能学院，北京邮电大学） ； State Key Laboratory of Multimedia Information Processing, School of Computer Science, the National Engineering Research Center of Visual Technology, School of Computer Science, and the PKU-AI 2 Robotics Joint Lab of Embodied AI, Peking University（多媒体信息处理国家重点实验室，计算机学院，视觉技术国家工程研究中心，计算机学院，北京大学PKU-AI 2机器人联合实验室） ； Institute for Artificial Intelligence, the State Key Laboratory of Multimedia Information Processing, School of Computer Science, and the National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（人工智能研究院，多媒体信息处理国家重点实验室，计算机学院，视觉技术国家工程研究中心，计算机学院，北京大学） ； Institute for Artificial Intelligence, and the National Engineering Research Center of Visual Technology, School of Computer Science, Peking University（人工智能研究院，视觉技术国家工程研究中心，计算机学院，北京大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出一种基于模运算的HDR成像系统，通过改进传感模型和解调算法实现高速全彩HDR成像，有效克服了传统方法在运动伪影与信息损失之间的权衡问题。

Comments TPAMI under review

Physically Inspired Gaussian Splatting for HDR Novel View Synthesis

基于物理的高动态范围新型视图合成的高斯点散射

Huimin Zeng, Yue Bai, Hailing Wang, Yun Fu

机构 * Department of Electrical and Computer Engineering, Northeastern University（东北大学电气与计算机工程系） ； Khoury College of Computer Science, Northeastern University（东北大学Khoury计算机科学学院） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出PhysHDR-GS框架，通过建模内在反射率和可调环境光照，改进HDR-NVS在动态细节重建和光照依赖外观捕捉中的性能，实验表明在真实和合成数据集上具有更高的PSNR和实时渲染速度。

Comments Accepted to CVPR 2026

InstantHDR: Single-forward Gaussian Splatting for High Dynamic Range 3D Reconstruction

InstantHDR：单次前向高斯散射用于高动态范围3D重建

Dingqiang Ye, Jiacong Xu, Jianglu Ping, Yuxiang Guo, Chao Fan, Vishal M. Patel

机构 * Johns Hopkins University（约翰霍普金斯大学） ； Shenzhen University（深圳大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出InstantHDR，通过单次前向传递从未校准的多曝光LDR图像集重建HDR场景，采用几何引导的外观建模和元网络实现通用的场景特定色调映射，提升重建速度。

Anti-Aliasing Snapshot HDR Imaging Using Non-Regular Sensing

利用非规则传感的抗锯齿快照HDR成像

Teresa Stürzenhofäcker, Moritz Klimm, Jürgen Seiler, André Kaup

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 eess.IV

AI总结 本文提出了一种基于非规则像素排列的快照HDR传感器，通过空间变化孔径和非规则排列减少锯齿效应，实现高动态范围图像采集。

HDR Reconstruction Boosting with Training-Free and Exposure-Consistent Diffusion

通过无训练和曝光一致的扩散实现HDR重建增强

Yo-Tin Lin, Su-Kai Chen, Hou-Ning Hu, Yen-Yu Lin, Yu-Lun Liu

机构 * National Yang Ming Chiao Tung University（国家阳明交通大学） ； MediaTek Inc.（联发科公司） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 通过无训练和曝光一致的扩散技术提升HDR重建效果，增强过曝区域的图像质量并保持多曝光一致性。

Comments WACV 2026. Project page: https://github.com/EusdenLin/HDR-Reconstruction-Boosting

A Hardware-Algorithm Co-Designed Framework for HDR Imaging and Dehazing in Extreme Rocket Launch Environments

面向极端火箭发射环境的HDR成像与去雾联合设计框架

Jing Tao, Banglei Guan, Pengju Sun, Taihang Lei, Yang Shang, Qifeng Yu

机构 * College of Aerospace Science and Engineering（航空航天科学与工程学院） ； National University of Defense Technology（国防科技大学） ； Hunan Provincial Key Laboratory of Image Measurement and Vision Navigation（湖南省图像测量与视觉导航重点实验室） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出一种结合定制SVE传感器和物理感知去雾算法的联合设计框架，用于在极端火箭发射环境下实现HDR成像与去雾，提升图像质量以支持机械参数的精确分析。

Comments The paper has been accepted by Acta Mechanica Sinica

ExReg: Wide-range Photo Exposure Correction via a Multi-dimensional Regressor with Attention

ExReg：通过带有注意力机制的多维回归器实现宽范围照片曝光校正

Huu-Phu Do, Hao-Chien Hsueh, Tzu-Hao Chiang, Chi-Han Chen, Wen-Hsiao Peng, Ching-Chun Huang

机构 * National Yang Ming Chiao Tung University 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 ExReg通过多维回归和注意力机制，解决宽范围照片曝光校正问题，实现高效且准确的曝光调整。

Comments Accepted by ACM Transactions on Intelligent Systems and Technology

Simultaneous Enhancement and Noise Suppression under Complex Illumination Conditions

在复杂光照条件下同时实现增强与去噪

Jing Tao, You Li, Banglei Guan, Yang Shang, Qifeng Yu

机构 * College of Aerospace Science, National University of Defense Technology（航天科学学院，国防科技大学） ； Key Laboratory of Human Factors Engineering, China Astronaut Research and Training Center（人因工程重点实验室，中国航天员科研训练中心） ； College of Aerospace Science and Engineering, National University of Defense Technology（航空航天工程学院，国防科技大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

AI总结 本文提出了一种在复杂光照条件下同时实现图像增强和去噪的新框架，通过梯度域加权引导滤波和Retinex模型分解光照与反射层，结合多曝光融合和线性拉伸策略，提升图像质量与对比度。

Comments The paper has been accepted and officially published by IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT

LoopExpose: An Unsupervised Framework for Arbitrary-Length Exposure Correction

Ao Li, Chen Chen, Zhenyu Wang, Tao Huang, Fangfang Wu, Weisheng Dong

机构 * School of Artificial Intelligence, Xidian University（西安电子科技大学人工智能学院） ； Hangzhou Institue of Technology, Xidian University（西安电子科技大学杭州学院） ； School of Computer Science and Technology, Xidian University（西安电子科技大学计算机科学与技术学院） ； School of Information Science and Engineering, Dalian University of Technology（大连理工大学信息科学与工程学院） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Learning Neural Exposure Fields for View Synthesis

Michael Niemeyer, Fabian Manhardt, Marie-Julie Rakotosaona, Michael Oechsle, Christina Tsalicoglou, Keisuke Tateno, Jonathan T. Barron, Federico Tombari

机构 * Google（谷歌） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments Accepted to NeurIPS 2025. Project page available at https://m-niemeyer.github.io/nexf/index.html

DiffCamera: Arbitrary Refocusing on Images

Yiyang Wang, Xi Chen, Xiaogang Xu, Yu Liu, Hengshuang Zhao

机构 * The University of Hong Kong（香港大学） ； The Chinese University of Hong Kong（香港中文大学） ； Tongyi Lab（通义实验室） 纠错

专题命中 多聚焦/多曝光融合 ：multi-focus(abstract)；分类 cs.CV

More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning

Luong Tran, Thieu Vo, Anh Nguyen, Sang Dinh, Van Nguyen

机构 * FPT Software AI Center（FPT软件人工智能中心） ； National University of Singapore（新加坡国立大学） ； University of Liverpool（利物浦大学） ； Hanoi University of Science and Technology（河内科学技术大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-focus(abstract)；分类 cs.CV

Comments ICCV 2025

UNICE: Training A Universal Image Contrast Enhancer

Ruodai Cui, Lei Zhang

机构 * Department of Computing, The Hong Kong Polytechnic University（计算系，香港理工大学） 纠错

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

HDRGS: High Dynamic Range Gaussian Splatting

Jiahao Wu, Lu Xiao, Rui Peng, Kaiqiang Xiong, Ronggang Wang

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

HDRTransDC: High Dynamic Range Image Reconstruction with Transformer Deformation Convolution

Shuaikang Shang, Xuejing Kang, Anlong Ming

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments We request to withdraw our manuscript due to identified issues: inaccuracies in the description of a submodule's composition, principles, and functionality in Section 3.2, and potential problems in metric calculation in Sections 4.2 and 4.3. To prevent the spread of misleading information, we believe it is necessary to temporarily withdraw the manuscript for further research and verification

Improving Bracket Image Restoration and Enhancement with Flow-guided Alignment and Enhanced Feature Aggregation

Wenjie Lin, Zhen Liu, Chengzhi Jiang, Mingyan Han, Ting Jiang, Shuaicheng Liu

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Exposing the Unseen: Exposure Time Emulation for Offline Benchmarking of Vision Algorithms

Olivier Gamache, Jean-Michel Fortin, Matěj Boxan, Maxime Vaidis, François Pomerleau, Philippe Giguère

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.RO

Comments 8 pages, 6 figures, submitted to 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2024)

High Dynamic Range Imaging of Dynamic Scenes with Saturation Compensation but without Explicit Motion Compensation

Haesoo Chung, Nam Ik Cho

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments WACV 2022

Learning Regularized Multi-Scale Feature Flow for High Dynamic Range Imaging

Qian Ye, Masanori Suganuma, Jun Xiao, Takayuki Okatani

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Adaptive Weighted Guided Image Filtering for Depth Enhancement in Shape-From-Focus

Yuwen Li, Zhengguo Li, Chaobing Zheng, Shiqian Wu

专题命中 多聚焦/多曝光融合 ：multi-focus(abstract)；分类 cs.CV

A Method For Adding Motion-Blur on Arbitrary Objects By using Auto-Segmentation and Color Compensation Techniques

Michihiro Mikamo, Ryo Furukawa, Hiroshi Kawasaki

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments This paper was accepted at ICIP 2021

Journal ref 2021 IEEE International Conference on Image Processing (ICIP)

Quality Assessment for Tone-Mapped HDR Images Using Multi-Scale and Multi-Layer Information

Qin He, Dingquan Li, Tingting Jiang, Ming Jiang

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.MM

Comments This paper has 6 pages, 3 tables and 2 figures in total, corrects a typo in the accepted version

Journal ref Proceedings of 2018 IEEE International Conference on Multimedia and Expo Workshops (ICMEW)

Learning a Reinforced Agent for Flexible Exposure Bracketing Selection

Zhouxia Wang, Jiawei Zhang, Mude Lin, Jiong Wang, Ping Luo, Jimmy Ren

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments to be published in CVPR 2020

No Fear of the Dark: Image Retrieval under Varying Illumination Conditions

Tomas Jenicek, Ondřej Chum

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

High-Dynamic-Range Imaging for Cloud Segmentation

Soumyabrata Dev, Florian M. Savoy, Yee Hui Lee, Stefan Winkler

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments Published in Atmospheric Measurement Techniques (AMT), 2018

DeepFuse: A Deep Unsupervised Approach for Exposure Fusion with Extreme Exposure Image Pairs

K. Ram Prabhakar, V. Sai Srikar, R. Venkatesh Babu

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Comments ICCV 2017

Generation of High Dynamic Range Illumination from a Single Image for the Enhancement of Undesirably Illuminated Images

Jae Sung Park, Nam Ik Cho

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

Efficient Image Retargeting for High Dynamic Range Scenes

Govind Salvi, Puneet Sharma, Shanmuganathan Raman

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)；分类 cs.CV

A Two-level Radial-velocity Zero-point Calibration for LAMOST MRS with Gaia and APOGEE and a Value-added RV Catalogue

基于Gaia和APOGEE的LAMOST MRS的两级视向速度零点校准及增值视向速度星表

Jinming Zhang, Haibo Yuan

专题命中 多聚焦/多曝光融合 ：multi-exposure(abstract)

AI总结 该研究针对LAMOST MRS的RV零点系统误差，提出两级校准方法并发布增值星表，使RV精度提升约2倍，支持跨多维度的一致视向速度分析。

Comments 18 pages, 12 figures. Catalogue available at https://doi.org/10.5281/zenodo.21467895 ; pipeline at https://github.com/CrotRest/lamost-mrs-rvzp. Accepted by ApJS