Unprocessing Images for Learned Raw Denoising
| Autor: | Tim Brooks, Jonathan T. Barron, Dillon Sharlet, Jiawen Chen, Ben Mildenhall, Tianfan Xue |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
FOS: Computer and information sciences
Computer Science - Machine Learning business.industry Computer science Computer Vision and Pattern Recognition (cs.CV) Color correction Noise reduction Pipeline (computing) Computer Science - Computer Vision and Pattern Recognition ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION 020206 networking & telecommunications Image processing 02 engineering and technology Tone mapping Real image Convolutional neural network Machine Learning (cs.LG) Computational photography 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Computer vision Noise (video) Artificial intelligence Image sensor business |
| Zdroj: | CVPR |
| DOI: | 10.1109/cvpr.2019.01129 |
| Popis: | Machine learning techniques work best when the data used for training resembles the data used for evaluation. This holds true for learned single-image denoising algorithms, which are applied to real raw camera sensor readings but, due to practical constraints, are often trained on synthetic image data. Though it is understood that generalizing from synthetic to real data requires careful consideration of the noise properties of image sensors, the other aspects of a camera's image processing pipeline (gain, color correction, tone mapping, etc) are often overlooked, despite their significant effect on how raw measurements are transformed into finished images. To address this, we present a technique to "unprocess" images by inverting each step of an image processing pipeline, thereby allowing us to synthesize realistic raw sensor measurements from commonly available internet photos. We additionally model the relevant components of an image processing pipeline when evaluating our loss function, which allows training to be aware of all relevant photometric processing that will occur after denoising. By processing and unprocessing model outputs and training data in this way, we are able to train a simple convolutional neural network that has 14%-38% lower error rates and is 9x-18x faster than the previous state of the art on the Darmstadt Noise Dataset, and generalizes to sensors outside of that dataset as well. http://timothybrooks.com/tech/unprocessing/ |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|