Raw Instinct: Trust Your Classifiers and Skip the Conversion (2403.14439v1)
Abstract: Using RAW-images in computer vision problems is surprisingly underexplored considering that converting from RAW to RGB does not introduce any new capture information. In this paper, we show that a sufficiently advanced classifier can yield equivalent results on RAW input compared to RGB and present a new public dataset consisting of RAW images and the corresponding converted RGB images. Classifying images directly from RAW is attractive, as it allows for skipping the conversion to RGB, lowering computation time significantly. Two CNN classifiers are used to classify the images in both formats, confirming that classification performance can indeed be preserved. We furthermore show that the total computation time from RAW image data to classification results for RAW images can be up to 8.46 times faster than RGB. These results contribute to the evidence found in related works, that using RAW images as direct input to computer vision algorithms looks very promising.
- R. Nguyen and M. Brown, “Raw image reconstruction using a self-contained srgb–jpeg image with small memory overhead,” in International Journal of Computer Vision, 2017.
- Yasir Salih, Wazirah bt. Md-Esa, Aamir S. Malik, and Naufal Saad, “Tone mapping of hdr images: A review,” in 2012 4th International Conference on Intelligent and Advanced Systems (ICIAS2012), 2012.
- Hakki Can and Michael Brown, “Beyond raw-rgb and srgb: Advocating access to a colorimetric image state,” in Color and Imaging Conference, 2019.
- Z. Zhang, H. Wang, M. Liu, R. Wang, J. Zhang, and W. Zuo, “Learning raw-to-srgb mappings with inaccurately aligned supervision,” in International Conference on Computer Vision, 2021.
- Lu Yuan and Jian Sun, “High quality image reconstruction from raw and jpeg image pair,” in International Conference on Computer Vision, 2011.
- Seonghyeon Nam, Abhijith Punnappurath, Marcus A. Brubaker, and Michael S. Brown, “Learning srgb-to-raw-rgb de-rendering with content-aware metadata,” in Conference on Computer Vision and Pattern Recognition, 2022.
- Zhou Wei, Zhang Xiangyu, Wang Shenghua Gao Hongyu, and Lou Xin, “Raw bayer pattern image synthesis for computer vision-oriented image signal processing pipeline design,” in Conference on Computer Vision and Pattern Recognition, 2021.
- Zhihao Li, Ming Lu, Xu Zhang, Xin Feng, M. Salman Asif, and Zhan Ma, “Efficient visual computing with camera raw snapshots,” in Conference on Computer Vision and Pattern Recognition, 2022.
- X. Zhang, Q. Chen, R. Ng, and V. Koltun, “Zoom to learn, learn to zoom,” in Conference on Computer Vision and Pattern Recognition, 2019.
- C. Chen, Q. Chen, J. Xiu, and V. Koltun, “Learning to see in the dark,” in Conference on Computer Vision and Pattern Recognition, 2018.
- C. Liang, Y. Chen, Y. Liu, and W. H. Hsu, “Raw image deblurring,” in IEEE Transactions on Multimedia, 2020.
- William Ljungbergh, Joakim Johnander, Christoffer Petersson, and Michael Felsberg, “Raw or cooked? object detection on raw images,” in Conference on Computer Vision and Pattern Recognition, 2023.
- Xiangyu Zhang, Ling Zhang, and Xin Lou, “A raw image-based end-to-end object detection accelerator using hog features,” in IEEE Transactions on Circuits and Systems I: Regular Papers, 2022.
- Igor Morawski, Yu-An Chen, Yu-Sheng Lin, Shusil Dangi, Kai He, and Winston H. Hsu, “Genisp: Neural isp for low-light machine cognition,” in Conference on Computer Vision and Pattern Recognition, 2022.
- K. Simonyan and A. Zisserman, “Very deep convolutional networks for large-scale image recognition,” in Conference on Computer Vision and Pattern Recognition, 2014.
- K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Conference on Computer Vision and Pattern Recognition, 2016.
- A. Omid-Zohoor, C. Young, and B. Murmann D. Ta, “Pascalraw: Raw image database for object detection in searchworks catalog,” in Stanford Digital Repository, 2014.
- D.-T. Dang-Nguyen, C. Pasquini, V. Conotter, and G. Boato, “Raise - a raw images dataset for digital image forensics,” in ACM Multimedia Systems Conference, 2015.
- V. Bychkovsky, S. Paris, and F. Durand E. Chan, “Learning photographic global tonal adjustment with a database of input / output image pairs,” in Conference on Computer Vision and Pattern Recognition, 2011.
- Phase One, “Software Development Kits (SDK).” https://geospatial.phaseone.com/resources-support/developer/sdk/. (accessed Nov. 28, 2022).
- Nungnit Wattanavichean, Jirasin Boonchai, Sasithon Yodthong, Chakkrit Preuksakarn, Huang S.C.-H, and Thattapon Surasak, “Gfp pattern recognition in raman spectra by modified vgg networks for localisation tracking in living cells,” in Engineering Journal, vol. 25, 2021.
Collections
Sign up for free to add this paper to one or more collections.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.