面向移动设备极低光照超高清视频的高效实时 raw-to-raw 去噪
Efficient Real-Time Raw-to-Raw Denoising for Extreme Low-Light Ultra HD Video on Mobile Devices
面向移动端 ISP 前端的 raw-to-raw 视频去噪方案：把重参数化、结构重排与量化组合进训练后优化流程，在 <33ms、<250mA 的约束下跑 4K/8K 视频，可直接迁移到其他需要在端侧实时部署的低层视觉模型压缩与部署流程。
原文依据 Efficient training and post-training optimizations (reparameterization, restructuring, quantization) to meet latency constraints
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论深度神经网络（DNN）的最新进展显著提升了相机在低光照（<10lx）条件下拍摄的视觉质量，但在极低光照（<1lx）条件下的视觉质量仍不理想。现有 DNN 模型计算量大、处理时间长，难以用于高分辨率视频的实时增强。因此，在极低光照环境下拍摄的超高清（UHD）视频（4K/8K）噪声更强、细节更少。为 UHD 视频开发基于 DNN 的增强方案面临诸多挑战，包括配对数据集的构建、时序一致性，以及在严格延迟（<33ms）与功耗（30fps 视频下 <250mA）约束下的高效部署。我们提出一套完整的方法论，用于开发极低光照下 UHD 视频的实时 raw-to-raw 去噪方案，并可无缝集成到现有 ISP 流水线中。与替换 ISP 的方案不同，我们的方案可跨传感器平台增强商用相机栈。我们的框架包括：（1）多样化的数据集构建方法；（2）面向移动端计算单元优化的低复杂度模型架构；（3）高效的训练与训练后优化（重参数化、结构重排、量化），以满足延迟约束并保证高质量输出。最终得到一个高能效的实时 raw-to-raw 视频去噪器，在保持下游 ISP 行为的同时提升极低光照视频质量。
英文原文摘要 1519 字符
Recent advancements in deep neural networks (DNNs) have significantly improved visual quality of camera captures under low-light (<10lx) conditions, yet visual quality in extreme low-light (<1lx) remains inadequate. Existing DNN models are computationally intensive and suffer from large processing times, making them impractical for real-time enhancement of high-resolution video. Consequently, Ultra HD (UHD) videos (4K/8K) captured in extreme low-light environments exhibit elevated noise and diminished detail. Developing DNN-based solutions for UHD video enhancement faces challenges including paired dataset creation, temporal consistency, and efficient deployment under strict latency (<33ms) and power constraints (<250mA for 30fps video).We present a comprehensive methodology for developing a real-time raw to raw denoising solution for UHD video in extreme low-light, designed for seamless integration into existing ISP pipelines. Unlike ISP-replacement approaches, our solution enhances commercial camera stacks across sensor platforms. Our framework comprises: (1) Diverse dataset creation methodology; (2) A low-complexity model architecture optimized for mobile compute elements; (3) Efficient training and post-training optimizations (reparameterization, restructuring, quantization) to meet latency constraints while ensuring high-quality output. The result is a power-efficient real-time raw to raw video denoiser that improves extreme low-light video quality while preserving downstream ISP behavior.