Rethinking Model Redundancy for Low-light Image Enhancement
- URL: http://arxiv.org/abs/2412.16459v1
- Date: Sat, 21 Dec 2024 03:17:28 GMT
- Title: Rethinking Model Redundancy for Low-light Image Enhancement
- Authors: Tong Li, Lizhi Wang, Hansen Feng, Lin Zhu, Wanxuan Lu, Hua Huang,
- Abstract summary: Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images.
Recent advancements primarily focus on customizing complex neural network models, but we have observed significant redundancy in these models, limiting further performance improvement.
Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance.
- Score: 21.864075752556452
- License:
- Abstract: Low-light image enhancement (LLIE) is a fundamental task in computational photography, aiming to improve illumination, reduce noise, and enhance the image quality of low-light images. While recent advancements primarily focus on customizing complex neural network models, we have observed significant redundancy in these models, limiting further performance improvement. In this paper, we investigate and rethink the model redundancy for LLIE, identifying parameter harmfulness and parameter uselessness. Inspired by the rethinking, we propose two innovative techniques to mitigate model redundancy while improving the LLIE performance: Attention Dynamic Reallocation (ADR) and Parameter Orthogonal Generation (POG). ADR dynamically reallocates appropriate attention based on original attention, thereby mitigating parameter harmfulness. POG learns orthogonal basis embeddings of parameters and prevents degradation to static parameters, thereby mitigating parameter uselessness. Experiments validate the effectiveness of our techniques. We will release the code to the public.
Related papers
- Unsupervised Low-light Image Enhancement with Lookup Tables and Diffusion Priors [38.96909959677438]
Low-light image enhancement (LIE) aims at precisely and efficiently recovering an image degraded in poor illumination environments.
Recent advanced LIE techniques are using deep neural networks, which require lots of low-normal light image pairs, network parameters, and computational resources.
We devise a novel unsupervised LIE framework based on diffusion priors and lookup tables to achieve efficient low-light image recovery.
arXiv Detail & Related papers (2024-09-27T16:37:27Z) - SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation [52.6922833948127]
In this work, we investigate the importance of parameters in pre-trained diffusion models.
We propose a novel model fine-tuning method to make full use of these ineffective parameters.
Our method enhances the generative capabilities of pre-trained models in downstream applications.
arXiv Detail & Related papers (2024-09-10T16:44:47Z) - Efficient Learning With Sine-Activated Low-rank Matrices [25.12262017296922]
We propose a novel theoretical framework that integrates a sinusoidal function within the low-rank decomposition process.
Our method proves to be a plug in enhancement for existing low-rank models, as evidenced by its successful application in Vision Transformers (ViT), Large Language Models (LLMs), Neural Radiance Fields (NeRF) and 3D shape modelling.
arXiv Detail & Related papers (2024-03-28T08:58:20Z) - Zero-Reference Lighting Estimation Diffusion Model for Low-Light Image Enhancement [2.9873893715462185]
We propose a novel zero-reference lighting estimation diffusion model for low-light image enhancement called Zero-LED.
It utilizes the stable convergence ability of diffusion models to bridge the gap between low-light domains and real normal-light domains.
It successfully alleviates the dependence on pairwise training data via zero-reference learning.
arXiv Detail & Related papers (2024-03-05T11:39:17Z) - LIR: A Lightweight Baseline for Image Restoration [4.187190284830909]
The inherent characteristics of the Image Restoration task are often overlooked in many works.
We propose a Lightweight Baseline network for Image Restoration called LIR to efficiently restore the image and remove degradations.
Our LIR achieves the state-of-the-art Structure Similarity Index Measure (SSIM) and comparable performance to state-of-the-art models on Peak Signal-to-Noise Ratio (PSNR)
arXiv Detail & Related papers (2024-02-02T12:39:47Z) - DGNet: Dynamic Gradient-Guided Network for Water-Related Optics Image
Enhancement [77.0360085530701]
Underwater image enhancement (UIE) is a challenging task due to the complex degradation caused by underwater environments.
Previous methods often idealize the degradation process, and neglect the impact of medium noise and object motion on the distribution of image features.
Our approach utilizes predicted images to dynamically update pseudo-labels, adding a dynamic gradient to optimize the network's gradient space.
arXiv Detail & Related papers (2023-12-12T06:07:21Z) - LDM-ISP: Enhancing Neural ISP for Low Light with Latent Diffusion Models [54.93010869546011]
We propose to leverage the pre-trained latent diffusion model to perform the neural ISP for enhancing extremely low-light images.
Specifically, to tailor the pre-trained latent diffusion model to operate on the RAW domain, we train a set of lightweight taming modules.
We observe different roles of UNet denoising and decoder reconstruction in the latent diffusion model, which inspires us to decompose the low-light image enhancement task into latent-space low-frequency content generation and decoding-phase high-frequency detail maintenance.
arXiv Detail & Related papers (2023-12-02T04:31:51Z) - No Parameters Left Behind: Sensitivity Guided Adaptive Learning Rate for
Training Large Transformer Models [132.90062129639705]
We propose a novel training strategy that encourages all parameters to be trained sufficiently.
A parameter with low sensitivity is redundant, and we improve its fitting by increasing its learning rate.
In contrast, a parameter with high sensitivity is well-trained and we regularize it by decreasing its learning rate to prevent further overfitting.
arXiv Detail & Related papers (2022-02-06T00:22:28Z) - Invertible Network for Unpaired Low-light Image Enhancement [78.33382003460903]
We propose to leverage the invertible network to enhance low-light image in forward process and degrade the normal-light one inversely with unpaired learning.
In addition to the adversarial loss, we design various loss functions to ensure the stability of training and preserve more image details.
We present a progressive self-guided enhancement process for low-light images and achieve favorable performance against the SOTAs.
arXiv Detail & Related papers (2021-12-24T17:00:54Z) - Universal and Flexible Optical Aberration Correction Using Deep-Prior
Based Deconvolution [51.274657266928315]
We propose a PSF aware plug-and-play deep network, which takes the aberrant image and PSF map as input and produces the latent high quality version via incorporating lens-specific deep priors.
Specifically, we pre-train a base model from a set of diverse lenses and then adapt it to a given lens by quickly refining the parameters.
arXiv Detail & Related papers (2021-04-07T12:00:38Z)
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.