English
Related papers

Related papers: Syn2Real Transfer Learning for Image Deraining usi…

200 papers

Recent CNN-based methods for image deraining have achieved excellent performance in terms of reconstruction error as well as visual quality. However, these methods are limited in the sense that they can be trained only on fully labeled…

Computer Vision and Pattern Recognition · Computer Science 2020-09-29 Rajeev Yasarla , V. A. Sindagi , V. M. Patel

Removing the rain streaks from single image is still a challenging task, since the shapes and directions of rain streaks in the synthetic datasets are very different from real images. Although supervised deep deraining networks have…

Computer Vision and Pattern Recognition · Computer Science 2021-04-08 Yanyan Wei , Zhao Zhang , Yang Wang , Haijun Zhang , Mingbo Zhao , Mingliang Xu , Meng Wang

Despite great success in human parsing, progress for parsing other deformable articulated objects, like animals, is still limited by the lack of labeled data. In this paper, we use synthetic images and ground truth generated from CAD animal…

Computer Vision and Pattern Recognition · Computer Science 2020-04-07 Jiteng Mu , Weichao Qiu , Gregory Hager , Alan Yuille

Existing approaches for restoring weather-degraded images follow a fully-supervised paradigm and they require paired data for training. However, collecting paired data for weather degradations is extremely challenging, and existing methods…

Computer Vision and Pattern Recognition · Computer Science 2022-04-26 Rajeev Yasarla , Vishwanath A. Sindagi , Vishal M. Patel

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…

Computer Vision and Pattern Recognition · Computer Science 2024-07-30 Yunhao Ba , Howard Zhang , Ethan Yang , Akira Suzuki , Arnold Pfahnl , Chethan Chinder Chandrappa , Celso de Melo , Suya You , Stefano Soatto , Alex Wong , Achuta Kadambi

Deep neural networks produce state-of-the-art results when trained on a large number of labeled examples but tend to overfit when small amounts of labeled examples are used for training. Creating a large number of labeled examples requires…

Computer Vision and Pattern Recognition · Computer Science 2021-09-13 Attaullah Sahito , Eibe Frank , Bernhard Pfahringer

Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - a photo-realistic synthetic dataset consisting of more than 100,000 4K images of more than 20 types of micro aerial vehicles (MAVs). The…

Computer Vision and Pattern Recognition · Computer Science 2020-10-19 Ty Nguyen , Ian D. Miller , Avi Cohen , Dinesh Thakur , Shashank Prasad , Camillo J. Taylor , Pratik Chaudrahi , Vijay Kumar

Deep learning-based image denoising techniques often struggle with poor generalization performance to out-of-distribution real-world noise. To tackle this challenge, we propose a novel noise translation framework that performs denoising on…

Image and Video Processing · Electrical Eng. & Systems 2026-04-03 Inju Ha , Donghun Ryou , Seonguk Seo , Bohyung Han

Supervised deep learning has become the method of choice for image denoising. It involves the training of neural networks on large datasets composed of pairs of noisy and clean images. However, the necessity of training data that are…

Computer Vision and Pattern Recognition · Computer Science 2025-07-10 Sébastien Herbreteau , Michael Unser

Deep learning has revolutionized medical imaging, but its effectiveness is severely limited by insufficient labeled training data. This paper introduces a novel GAN-based semi-supervised learning framework specifically designed for low…

Computer Vision and Pattern Recognition · Computer Science 2025-08-11 Guido Manni , Clemente Lauretti , Loredana Zollo , Paolo Soda

Due to the difficulty in collecting paired real-world training data, image deraining is currently dominated by supervised learning with synthesized data generated by e.g., Photoshop rendering. However, the generalization to real rainy…

Computer Vision and Pattern Recognition · Computer Science 2022-08-30 Yinglong Wang , Chao Ma , Jianzhuang Liu

Training a deep network to perform semantic segmentation requires large amounts of labeled data. To alleviate the manual effort of annotating real images, researchers have investigated the use of synthetic data, which can be labeled…

Computer Vision and Pattern Recognition · Computer Science 2018-07-18 Fatemeh Sadat Saleh , Mohammad Sadegh Aliakbarian , Mathieu Salzmann , Lars Petersson , Jose M. Alvarez

Deep learning approaches in image processing predominantly resort to supervised learning. A majority of methods for image denoising are no exception to this rule and hence demand pairs of noisy and corresponding clean images. Only recently…

Image and Video Processing · Electrical Eng. & Systems 2020-10-02 Priyatham Kattakinda , A. N. Rajagopalan

We present a method to improve the visual realism of low-quality, synthetic images, e.g. OpenGL renderings. Training an unpaired synthetic-to-real translation network in image space is severely under-constrained and produces visible…

Computer Vision and Pattern Recognition · Computer Science 2020-03-31 Sai Bi , Kalyan Sunkavalli , Federico Perazzi , Eli Shechtman , Vladimir Kim , Ravi Ramamoorthi

Conditional Generative Adversarial Networks (GANs) for cross-domain image-to-image translation have made much progress recently. Depending on the task complexity, thousands to millions of labeled image pairs are needed to train a…

Computer Vision and Pattern Recognition · Computer Science 2018-10-12 Zili Yi , Hao Zhang , Ping Tan , Minglun Gong

Training deep networks with limited labeled data while achieving a strong generalization ability is key in the quest to reduce human annotation efforts. This is the goal of semi-supervised learning, which exploits more widely available…

Computer Vision and Pattern Recognition · Computer Science 2021-04-14 Daiqing Li , Junlin Yang , Karsten Kreis , Antonio Torralba , Sanja Fidler

Performance achievable by modern deep learning approaches are directly related to the amount of data used at training time. Unfortunately, the annotation process is notoriously tedious and expensive, especially for pixel-wise tasks like…

Computer Vision and Pattern Recognition · Computer Science 2018-10-16 Pierluigi Zama Ramirez , Alessio Tonioni , Luigi Di Stefano

It's useful to automatically transform an image from its original form to some synthetic form (style, partial contents, etc.), while keeping the original structure or semantics. We define this requirement as the "image-to-image translation"…

Computer Vision and Pattern Recognition · Computer Science 2017-01-11 Hao Dong , Paarth Neekhara , Chao Wu , Yike Guo

Semi-supervised learning (SSL) is a promising approach for training deep classification models using labeled and unlabeled datasets. However, existing SSL methods rely on a large unlabeled dataset, which may not always be available in many…

Machine Learning · Computer Science 2023-09-29 Shin'ya Yamaguchi

Domain randomization through synthesis is a powerful strategy to train networks that are unbiased with respect to the domain of the input images. Randomization allows networks to see a virtually infinite range of intensities and artifacts…

Computer Vision and Pattern Recognition · Computer Science 2026-04-23 Xiaoling Hu , Xiangrui Zeng , Oula Puonti , Juan Eugenio Iglesias , Bruce Fischl , Yael Balbastre
‹ Prev 1 2 3 10 Next ›