Learning Adaptive Lighting via Channel-Aware Guidance
- URL: http://arxiv.org/abs/2412.01493v1
- Date: Mon, 02 Dec 2024 13:44:53 GMT
- Title: Learning Adaptive Lighting via Channel-Aware Guidance
- Authors: Qirui Yang, Peng-Tao Jiang, Hao Zhang, Jinwei Chen, Bo Li, Huanjing Yue, Jingyu Yang,
- Abstract summary: Learning Adaptive Lighting Network (LALNet) is a unified framework capable of processing different light-related tasks.
We introduce color-separated features that emphasize the light difference of different color channels and combine them with traditional color-mixed features.
Experiments on four representative light-related tasks demonstrate that LALNet significantly outperforms state-of-the-art methods on benchmark tests.
- Score: 22.594897891133556
- License:
- Abstract: Learning lighting adaption is a key step in obtaining a good visual perception and supporting downstream vision tasks. There are multiple light-related tasks (e.g., image retouching and exposure correction) and previous studies have mainly investigated these tasks individually. However, we observe that the light-related tasks share fundamental properties: i) different color channels have different light properties, and ii) the channel differences reflected in the time and frequency domains are different. Based on the common light property guidance, we propose a Learning Adaptive Lighting Network (LALNet), a unified framework capable of processing different light-related tasks. Specifically, we introduce the color-separated features that emphasize the light difference of different color channels and combine them with the traditional color-mixed features by Light Guided Attention (LGA). The LGA utilizes color-separated features to guide color-mixed features focusing on channel differences and ensuring visual consistency across channels. We introduce dual domain channel modulation to generate color-separated features and a wavelet followed by a vision state space module to generate color-mixed features. Extensive experiments on four representative light-related tasks demonstrate that LALNet significantly outperforms state-of-the-art methods on benchmark tests and requires fewer computational resources. We provide an anonymous online demo at https://xxxxxx2025.github.io/LALNet/.
Related papers
- LumiNet: Latent Intrinsics Meets Diffusion Models for Indoor Scene Relighting [13.433775723052753]
Given a source image and a target lighting image, LumiNet synthesizes a relit version of the source scene that captures the target's lighting.
LumiNet processes latent representations from two different images - preserving geometry and albedo from the source while transferring lighting characteristics from the target.
arXiv Detail & Related papers (2024-11-29T18:59:11Z) - Beyond Night Visibility: Adaptive Multi-Scale Fusion of Infrared and
Visible Images [49.75771095302775]
We propose an Adaptive Multi-scale Fusion network (AMFusion) with infrared and visible images.
First, we separately fuse spatial and semantic features from infrared and visible images, where the former are used for the adjustment of light distribution.
Second, we utilize detection features extracted by a pre-trained backbone that guide the fusion of semantic features.
Third, we propose a new illumination loss to constrain fusion image with normal light intensity.
arXiv Detail & Related papers (2024-03-02T03:52:07Z) - You Only Need One Color Space: An Efficient Network for Low-light Image Enhancement [50.37253008333166]
Low-Light Image Enhancement (LLIE) task tends to restore the details and visual information from corrupted low-light images.
We propose a novel trainable color space, named Horizontal/Vertical-Intensity (HVI)
It not only decouples brightness and color from RGB channels to mitigate the instability during enhancement but also adapts to low-light images in different illumination ranges due to the trainable parameters.
arXiv Detail & Related papers (2024-02-08T16:47:43Z) - Color Recognition in Challenging Lighting Environments: CNN Approach [0.0]
Researchers are working to enhance the color detection techniques for the application of computer vision.
To address this issue, a color detection method, which is based on a Convolutional Neural Network (CNN) is proposed.
It is experimentally verified that our method can substantially enhance the robustness of color detection in different lighting conditions.
arXiv Detail & Related papers (2024-02-07T11:26:00Z) - ColorVideoVDP: A visual difference predictor for image, video and display distortions [51.29162719944865]
metric is built on novel psychophysical models of chromatic contrast sensitivity and cross-channel contrast masking.
It accounts for the viewing conditions, geometric, and photometric characteristics of the display.
It was trained to predict common video streaming distortions and 8 new distortion types related to AR/VR displays.
arXiv Detail & Related papers (2024-01-21T13:16:33Z) - Color Equivariant Convolutional Networks [50.655443383582124]
CNNs struggle if there is data imbalance between color variations introduced by accidental recording conditions.
We propose Color Equivariant Convolutions ( CEConvs), a novel deep learning building block that enables shape feature sharing across the color spectrum.
We demonstrate the benefits of CEConvs in terms of downstream performance to various tasks and improved robustness to color changes, including train-test distribution shifts.
arXiv Detail & Related papers (2023-10-30T09:18:49Z) - Brighten-and-Colorize: A Decoupled Network for Customized Low-Light
Image Enhancement [22.097267755811192]
Low-Light Image Enhancement (LLIE) aims to improve the perceptual quality of an image captured in low-light conditions.
Recent advances in this area mainly focus on the refinement of the lightness, while ignoring the role of chrominance.
In this work, a brighten-and-colorize'' network (called BCNet) is proposed to address the above issues.
arXiv Detail & Related papers (2023-08-06T06:04:16Z) - MIMT: Multi-Illuminant Color Constancy via Multi-Task Local Surface and
Light Color Learning [42.72878256074646]
We introduce a multi-task learning method to discount multiple light colors in a single input image.
To have better cues of the local surface/light colors under multiple light color conditions, we design a novel multi-task learning framework.
Our model achieves 47.1% improvement compared to a state-of-the-art multi-illuminant color constancy method on a multi-illuminant dataset.
arXiv Detail & Related papers (2022-11-16T09:00:20Z) - Planckian jitter: enhancing the color quality of self-supervised visual
representations [32.28858433165915]
We analyze how the traditionally used color jitter negatively impacts the quality of the color features in the learned feature representation.
We replace this module with physics-based color augmentation, called Planckian jitter, which creates realistic variations in chromaticity.
We show that the performance of the learned features is robust with respect to illuminant variations.
arXiv Detail & Related papers (2022-02-16T11:13:37Z) - End-to-end Multi-modal Video Temporal Grounding [105.36814858748285]
We propose a multi-modal framework to extract complementary information from videos.
We adopt RGB images for appearance, optical flow for motion, and depth maps for image structure.
We conduct experiments on the Charades-STA and ActivityNet Captions datasets, and show that the proposed method performs favorably against state-of-the-art approaches.
arXiv Detail & Related papers (2021-07-12T17:58:10Z) - Underwater Image Enhancement via Medium Transmission-Guided Multi-Color
Space Embedding [88.46682991985907]
We present an underwater image enhancement network via medium transmission-guided multi-color space embedding, called Ucolor.
Our network can effectively improve the visual quality of underwater images by exploiting multiple color spaces embedding.
arXiv Detail & Related papers (2021-04-27T07:35:30Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.