no code implementations • ECCV 2020 • Qili Deng, Ziling Huang, Chung-Chi Tsai, Chia-Wen Lin
In this paper, we present a Haze-Aware Representation Distillation Generative Adversarial Network named HardGAN for single-image dehazing.
no code implementations • 27 Mar 2024 • He-Hao Liao, Yan-Tsung Peng, Wen-Tao Chu, Ping-Chun Hsieh, Chung-Chi Tsai
The work aims to recover rain images by removing rain streaks via Self-supervised Reinforcement Learning (RL) for image deraining (SRL-Derain).
1 code implementation • 22 Dec 2023 • Fu-Jen Tsai, Yan-Tsung Peng, Chen-Yu Chang, Chan-Yu Li, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin
Besides, ViStripformer is an effective and efficient transformer architecture with much lower memory usage than the vanilla transformer.
no code implementations • 18 Dec 2023 • Jia-Hao Wu, Fu-Jen Tsai, Yan-Tsung Peng, Chung-Chi Tsai, Chia-Wen Lin, Yen-Yu Lin
We parameterize the blur patterns of a blurred image with their orientations and magnitudes as a pixel-wise blur condition map to simulate motion trajectories and implicitly represent them in a continuous space.
1 code implementation • 14 Oct 2022 • Po-Sheng Liu, Fu-Jen Tsai, Yan-Tsung Peng, Chung-Chi Tsai, Chia-Wen Lin, Yen-Yu Lin
Most previous deblurring methods were built with a generic model trained on blurred images and their sharp counterparts.
1 code implementation • 10 Apr 2022 • Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin
Images taken in dynamic scenes may contain unwanted motion blur, which significantly degrades visual quality.
Ranked #2 on Deblurring on RealBlur-R
1 code implementation • 19 Jan 2021 • Fu-Jen Tsai, Yan-Tsung Peng, Yen-Yu Lin, Chung-Chi Tsai, Chia-Wen Lin
Image motion blur results from a combination of object motions and camera shakes, and such blurring effect is generally directional and non-uniform.
Ranked #5 on Deblurring on RealBlur-R
1 code implementation • NeurIPS 2019 • Cheng-Chun Hsu, Kuang-Jui Hsu, Chung-Chi Tsai, Yen-Yu Lin, Yung-Yu Chuang
This paper presents a weakly supervised instance segmentation method that consumes training data with tight bounding box annotations.
Box-supervised Instance Segmentation Multiple Instance Learning +4
no code implementations • 13 May 2019 • Ziling Huang, Zheng Wang, Chung-Chi Tsai, Shin'ichi Satoh, Chia-Wen Lin
To gain the superiority of deep learning models, we treat a group as multiple persons and transfer the domain of a labeled ReID dataset to a G-ReID target dataset style to learn single representations.
no code implementations • ECCV 2018 • Kuang-Jui Hsu, Chung-Chi Tsai, Yen-Yu Lin, Xiaoning Qian, Yung-Yu Chuang
In this paper, we address co-saliency detection in a set of images jointly covering objects of a specific class by an unsupervised convolutional neural network (CNN).