面向高动态范围目标检测的实时场景自适应色调映射
Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
浏览论文内容
中文总结 AI 辅助
本文提出一种场景自适应实时色调映射方法，通过神经光度校准等技术解决HDR图像适配检测网络的问题，性能优于传统算法，可在NVIDIA Jetson平台实现4K HDR图像实时处理。
中文摘要 AI 辅助
高动态范围（HDR）图像凭借丰富的色调与细节还原能力，在增强计算机视觉系统（尤其是自动驾驶领域）方面具有重要潜力。然而，大多数嵌入式系统所用的神经网络均基于低动态范围（LDR）输入进行训练，在处理高位深HDR图像时，因极端动态范围带来的挑战会出现性能大幅下降。本文提出一种新颖的色调映射方法，不仅能弥合HDR RAW输入与检测网络所需的LDR sRGB之间的差距，还能与下游任务实现端到端优化。该方法不依赖传统图像信号处理（ISP）流水线，而是引入神经光度校准来规范动态范围，采用尺度不变局部色调映射模型以保留图像细节。此外，其架构还支持性能迁移微调，可实现从LDR sRGB图像到HDR RAW图像的高效适配，且成本极低。所提方法在极具挑战性的汽车HDR场景中，性能优于传统色调映射算法与先进AI-ISP方法，同时在NVIDIA Jetson平台上可实现4K高位深HDR输入的实时处理。
英文摘要
High-dynamic-range (HDR) images, with their rich tone and detail reproduction, hold significant potential to enhance computer vision systems, particularly in autonomous driving. However, most neural networks for embedded systems are trained on low-dynamic-range (LDR) inputs and suffer substantial performance degradation when handling high-bit-depth HDR images due to the challenges posed by extreme dynamic ranges. In this paper, we propose a novel tone mapping method that not only bridges the gap between HDR RAW inputs and the LDR sRGB requirements of detection networks but also achieves end-to-end optimization with downstream tasks. Instead of relying on the traditional image signal processing (ISP) pipeline, we introduce neural photometric calibration to regularize dynamic ranges and a scaling-invariant local tone mapping model to preserve image details. In addition, our architecture also supports performance transfer finetuning, enabling efficient adaptation from the LDR sRGB images to the HDR RAW images with minimal cost. The proposed method outperforms traditional tone mapping algorithms and advanced AI-ISP methods in challenging automotive HDR scenes. Moreover, our pipeline achieves real-time processing of 4K high-bit-depth HDR inputs on NVIDIA Jetson platforms.
发表机构
- School of Data Science, The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳）数据科学学院）
- Tianmushan Laboratory, Beihang University（北京航空航天大学天目山实验室）
- School of Artificial Intelligence, Nanjing University of Information Science and Technology（南京信息工程大学人工智能学院）
- Department of Automation, Tsinghua University（清华大学自动化系）
- Point Spread Technology（点扩散科技）
机构由 AI 辅助整理，请以论文原文为准。
