paper-with-me

Papers

DPEC: Dual-Path Error Compensation Method for Enhanced Low-Light Image Clarity

2024-06-28 · Shuang Wang, Qianwen Lu, Boxing Peng, Yihe Nie, Qingchuan Tao

For the task of low-light image enhancement, deep learning-based algorithms have demonstrated superiority and effectiveness compared to traditional methods. However, these methods, primarily based on Retinex theory, tend to overlook the noise and color distortions in input images, leading to significant noise amplification and local color distortions in enhanced results. To address these issues, we propose the Dual-Path Error Compensation (DPEC) method, designed to improve image quality under low-light conditions by preserving local texture details while restoring global image brightness without amplifying noise. DPEC incorporates precise pixel-level error estimation to capture subtle differences and an independent denoising mechanism to prevent noise amplification. We introduce the HIS-Retinex loss to guide DPEC's training, ensuring the brightness distribution of enhanced images closely aligns with real-world conditions. To balance computational speed and resource efficiency while training DPEC for a comprehensive understanding of the global context, we integrated the VMamba architecture into its backbone. Comprehensive quantitative and qualitative experimental results demonstrate that our algorithm significantly outperforms state-of-the-art methods in low-light image enhancement. The code is publicly available online at https://github.com/wangshuang233/DPEC.

📄 PDF Abstract BibTeX arXiv:2407.09553

Code (1)

wangshuang233/DPEC-VM 공식 구현 pytorch

Tasks

DenoisingImage EnhancementLow-Light Image Enhancement

Methods 이 논문이 사용한 방법론

SPEED The monocular depth estimation (MDE) is the task of estimating depth from a single frame. This information is an essential knowledge in many computer vision tasks such as scene…

Similar Papers 제목 키워드 기반

Woodpecker: Hallucination Correction for Multimodal Large Language Models

2023-10-24 · Shukang Yin, Chaoyou Fu, Sirui Zhao, Tong Xu 외

Hallucination is a big shadow hanging over the rapidly evolving Multimodal Large Language Models (MLLMs), referring to the phenomenon that the generated text is inconsistent with the image content. In order to mitigate h…

Hallucination

CNN Classifier for Just-in-Time Woodpeckers Detection and Deterrent

2021-07-21 · Alexander Greysukh

Woodpeckers can cause significant damage to homes, especially in suburban areas. There are a number of preventing and repelling methods including passive decoys, though these may only provide temporary relief. Subsequent…

PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation

2026-07-25 · Shaoheng Xu, Chunyi Sun, Jihui Zhang, Amy Bastine 외 arxiv

Image-source-method (ISM)-based room impulse response (RIR) simulation is a useful and physically interpretable tool for acoustic scene modeling, but full-order ISM becomes computationally expensive as the reflection ord…

RILQ: Rank-Insensitive LoRA-based Quantization Error Compensation for Boosting 2-bit Large Language Model Accuracy

2024-12-02 · Geonho Lee, Janghwan Lee, Sukjin Hong, Minsoo Kim 외

Low-rank adaptation (LoRA) has become the dominant method for parameter-efficient LLM fine-tuning, with LoRA-based quantization error compensation (LQEC) emerging as a powerful tool for recovering accuracy in compressed …

Computational EfficiencyLanguage ModelingLanguage ModellingLarge Language Model+1

EoRA: Training-free Compensation for Compressed LLM with Eigenspace Low-Rank Approximation

2024-10-28 · Shih-Yang Liu, Huck Yang, Chien-Yi Wang, Nai Chit Fung 외

In this work, we re-formulate the model compression problem into the customized compensation problem: Given a compressed model, we aim to introduce residual low-rank paths to compensate for compression errors under custo…

ARCMathModel CompressionQuantization+1