Arnold Pfahnl
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Research Interests
Arnold Pfahnl has a total of 13 co-authors. Here are the top co-authors by number of shared publications:
- Achuta Kadambi
Electrical and Computer Engineering, University of California, Los Angeles, 420 Westwood Plaza Los Angeles, CA, 90095, United States
2 shared publications - Akira Suzuki
University of California, Los Angeles
2 shared publications - Alex Wong
Yale University
2 shared publications - Celso M. de Melo
DEVCOM Army Research Laboratory
2 shared publications - Stefano Soatto
UCLA Vision Lab
2 shared publications - Suya You
DEVCOM Army Research Laboratory, Los Angeles, CA, USA
2 shared publications
Latest Publications
- 13 November 2022
- Published by Springer Nature
- p. 723-740
Not Just Streaks: Towards Ground Truth for Single Image Deraining
- 13 November 2022
- Published by Springer Nature
- p. 723-740
Not Just Streaks: Towards Ground Truth for Single Image Deraining
- Open Access
Not Just Streaks: Towards Ground Truth for Single Image Deraining
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image. As there exists no real-world dataset for deraining, current state-of-the-art methods rely on synthetic data and thus are limited by the sim2real domain gap; moreover, rigorous evaluation remains a challenge due to the absence of a real paired dataset. We fill this gap by collecting a real paired deraining dataset through meticulous control of non-rain variations. Our dataset enables paired training and quantitative evaluation for diverse real-world rain phenomena (e.g. rain streaks and rain accumulation). To learn a representation robust to rain phenomena, we propose a deep neural network that reconstructs the underlying scene by minimizing a rain-robust loss between rainy and clean images. Extensive experiments demonstrate that our model outperforms the state-of-the-art deraining methods on real rainy images under various conditions. Project website: https://visual.ee.ucla.edu/gt_rain.htm/.
Open AccessNot Just Streaks: Towards Ground Truth for Single Image Deraining
We propose a large-scale dataset of real-world rainy and clean image pairs and a method to remove degradations, induced by rain streaks and rain accumulation, from the image. As there exists no real-world dataset for deraining, current state-of-the-art methods rely on synthetic data and thus are limited by the sim2real domain gap; moreover, rigorous evaluation remains a challenge due to the absence of a real paired dataset. We fill this gap by collecting a real paired deraining dataset through meticulous control of non-rain variations. Our dataset enables paired training and quantitative evaluation for diverse real-world rain phenomena (e.g. rain streaks and rain accumulation). To learn a representation robust to rain phenomena, we propose a deep neural network that reconstructs the underlying scene by minimizing a rain-robust loss between rainy and clean images. Extensive experiments demonstrate that our model outperforms the state-of-the-art deraining methods on real rainy images under various conditions. Project website: https://visual.ee.ucla.edu/gt_rain.htm/.