Efficient Visual Computing with Camera RAW Snapshots
Zhihao Li, Ming Lu, Xu Zhang, Xin Feng, M. Salman Asif, and Zhan Ma

TL;DR
This paper introduces a novel RAW image processing framework that bypasses traditional ISP, enabling high-level semantic understanding and compression directly in RAW domain, improving accuracy and efficiency across various cameras.
Contribution
The paper presents the mbda-Vision framework with an unpaired CycleR2R network for RAW image processing without ISP, enhancing cross-camera generalization and computational efficiency.
Findings
RAW-domain object detection outperforms RGB-domain detection.
RAW image compression achieves better results than RGB-based methods.
Framework generalizes across different camera sensors.
Abstract
Conventional cameras capture image irradiance on a sensor and convert it to RGB images using an image signal processor (ISP). The images can then be used for photography or visual computing tasks in a variety of applications, such as public safety surveillance and autonomous driving. One can argue that since RAW images contain all the captured information, the conversion of RAW to RGB using an ISP is not necessary for visual computing. In this paper, we propose a novel -Vision framework to perform high-level semantic understanding and low-level compression using RAW images without the ISP subsystem used for decades. Considering the scarcity of available RAW image datasets, we first develop an unpaired CycleR2R network based on unsupervised CycleGAN to train modular unrolled ISP and inverse ISP (invISP) models using unpaired RAW and RGB images. We can then flexibly generate…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsAdvanced Image and Video Retrieval Techniques · Visual Attention and Saliency Detection · CCD and CMOS Imaging Sensors
MethodsHuMan(Expedia)||How do I get a human at Expedia? · *Communicated@Fast*How Do I Communicate to Expedia? · Average Pooling · Logistic Regression · Softmax · 1x1 Convolution · k-Means Clustering · Global Average Pooling · GAN Least Squares Loss · Residual Connection
