VALSE 论文速览 第192期：LED - 无需标定的RAW域去噪流程

论文题目：

Lighting every darkness in two pairs: A calibration-free pipeline for raw denoising

作者列表：

靳鑫 (南开大学)、肖嘉文 (南开大学)、韩凌昊 (南开大学）、郭春乐 (南开大学)、张瑞勋 (北京大学)、刘夏雷 (南开大学)、李重仪 (南开大学)

B站观看网址：

https://www.bilibili.com/video/BV1KS411w7gV/

论文摘要：

Calibration-based methods have dominated RAW image denoising under extremely low-light environments. However, these methods suffer from several main deficiencies: 1) the calibration procedure is laborious and time-consuming, 2) denoisers for different cameras are difficult to transfer, and 3) the discrepancy between synthetic noise and real noise is enlarged by high digital gain. To overcome the above shortcomings, we propose a calibration-free pipeline for Lighting Every Darkness (LED), regardless of the digital gain or camera sensor. Instead of calibrating the noise parameters and training repeatedly, our method could adapt to a target camera only with few-shot paired data and fine-tuning. In addition, well-designed structural modification during both stages alleviates the domain gap between synthetic and real noise without any extra computational cost. With 2 pairs for each additional digital gain (in total 6 pairs) and 0.5% iterations, our method achieves superior performance over other calibration-based methods.

参考文献：

[1] Jin, Xin, et al. "Lighting every darkness in two pairs: A calibration-free pipeline for raw denoising." IEEE/CVF International Conference on Computer Vision (ICCV), 2023.

论文链接：

[https://srameo.github.io/projects/led-iccv23/]

代码链接：

[https://github.com/Srameo/LED]

视频讲者简介：

靳鑫，南开大学二年级博士生，程明明教授团队，与李重仪以及郭春乐老师深度合作。研究方向为图像/视频修复，曾在计算机视觉顶会CVPR，ICCV，AAAI发表工作。此外还曾参与组织 CVPR 2024 Workshop: Mobile Intelligent Photography & Imaging.

个人主页：

https://srameo.github.io/

特别鸣谢本次论文速览主要组织者：

月度轮值AC：傅雪阳 (中国科学技术大学)