Deep reinforcement learning in computer vision: a comprehensive survey
Deep reinforcement learning augments the reinforcement learning framework and utilizes
the powerful representation of deep neural networks. Recent works have demonstrated the …
the powerful representation of deep neural networks. Recent works have demonstrated the …
Automated exposures selection for high dynamic range structured-light 3-D scanning
Structured light scanning has gained widespread applications in industrial metrology;
however, measuring objects that have large surface-reflectivity variations is challenging. For …
however, measuring objects that have large surface-reflectivity variations is challenging. For …
Spatially varying exposure with 2-by-2 multiplexing: Optimality and universality
The advancement of new digital image sensors has enabled the design of exposure
multiplexing schemes where a single image capture can have multiple exposures and …
multiplexing schemes where a single image capture can have multiple exposures and …
DRHDR: A dual branch residual network for multi-bracket high dynamic range imaging
J Marín-Vega, M Sloth… - Proceedings of the …, 2022 - openaccess.thecvf.com
We introduce DRHDR, a Dual branch Residual Convolutional Neural Network for Multi-
Bracket HDR Imaging. In order to address the challenges of fusing multiple brackets from …
Bracket HDR Imaging. In order to address the challenges of fusing multiple brackets from …
LA-HDR: Light adaptive HDR reconstruction framework for single LDR image considering varied light conditions
X Hu, L Shen, M Jiang, R Ma… - IEEE Transactions on …, 2022 - ieeexplore.ieee.org
The high dynamic range (HDR) image recovery from the low dynamic range (LDR) image
aims to estimate HDR image by decompressing luminance range and enhancing details of …
aims to estimate HDR image by decompressing luminance range and enhancing details of …
Fast and flexible stack‐based inverse tone mapping
N Zhang, Y Ye, Y Zhao, X Li… - CAAI Transactions on …, 2023 - Wiley Online Library
Inverse tone mapping technique is widely used to restore the lost textures from a single low
dynamic range image. Recently, many stack‐based deep inverse tone mapping networks …
dynamic range image. Recently, many stack‐based deep inverse tone mapping networks …
DRL-ISP: Multi-Objective Camera ISP with Deep Reinforcement Learning
In this paper, we propose a multi-objective camera ISP framework that utilizes Deep
Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and …
Reinforcement Learning (DRL) and camera ISP toolbox that consist of network-based and …
RL-SeqISP: Reinforcement Learning-Based Sequential Optimization for Image Signal Processing
Hardware image signal processing (ISP), aiming at converting RAW inputs to RGB images,
consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP …
consists of a series of processing blocks, each with multiple parameters. Traditionally, ISP …
[HTML][HTML] 深度学习时代图像融合技术进展
左一帆, 方玉明, 马柯德 - 2023 - cjig.cn
摘要为提升真实场景视觉信号的采集质量, 往往需要通过多种融合方式获取相应的图像, 例如,
多聚焦, 多曝光, 多光谱和多模态等. 针对视觉信号采集的以上特性, 图像融合技术旨在利用同一 …
多聚焦, 多曝光, 多光谱和多模态等. 针对视觉信号采集的以上特性, 图像融合技术旨在利用同一 …
meTMQI: multi-task and exposure-prior learning for Tone-Mapped Quality Index
M Jiang, L Shen, X Hu, M Hu, P An, T Tian - The Visual Computer, 2024 - Springer
With limited dynamic range in consumer-level photographs and electronic displays, high
dynamic range images can be rendered as the standard dynamic range image by tone …
dynamic range images can be rendered as the standard dynamic range image by tone …