paper-with-me

홈 › Papers

Ground Truth Free Denoising by Optimal Transport

2020-07-03 · Sören Dittmer, Carola-Bibiane Schönlieb, Peter Maass

We present a learned unsupervised denoising method for arbitrary types of data, which we explore on images and one-dimensional signals. The training is solely based on samples of noisy data and examples of noise, which -- critically -- do not need to come in pairs. We only need the assumption that the noise is independent and additive (although we describe how this can be extended). The method rests on a Wasserstein Generative Adversarial Network setting, which utilizes two critics and one generator.

📄 PDF Abstract BibTeX arXiv:2007.01575

Code (1)

sdittmer/gtfd 공식 구현 pytorch

Tasks

DenoisingGenerative Adversarial Network

Similar Papers 제목 키워드 기반

Unbalanced Optimal Transport: A Unified Framework for Object Detection

2023-07-05 · CVPR 2023 1 · Henri De Plaen, Pierre-François De Plaen, Johan A. K. Suykens, Marc Proesmans 외

During training, supervised object detection tries to correctly match the predicted bounding boxes and associated classification scores to the ground truth. This is essential to determine which predictions are to be push…

GPUObjectobject-detectionObject Detection

Do Neural Optimal Transport Solvers Work? A Continuous Wasserstein-2 Benchmark

2021-06-03 · NeurIPS 2021 12 · Alexander Korotin, Lingxiao Li, Aude Genevay, Justin Solomon 외

Despite the recent popularity of neural network-based solvers for optimal transport (OT), there is no standard quantitative way to evaluate their performance. In this paper, we address this issue for quadratic-cost trans…

Image Generation

Masked Autoencoders for Low dose CT denoising

2022-10-10 · Dayang Wang, Yongshun Xu, Shuo Han, Hengyong Yu

Low-dose computed tomography (LDCT) reduces the X-ray radiation but compromises image quality with more noises and artifacts. A plethora of transformer models have been developed recently to improve LDCT image quality. H…

DecoderDenoising

Mahalanobis Distance-based Multi-view Optimal Transport for Multi-view Crowd Localization

2024-09-03 · Qi Zhang, Kaiyi Zhang, Antoni B. Chan, Hui Huang

Multi-view crowd localization predicts the ground locations of all people in the scene. Typical methods usually estimate the crowd density maps on the ground plane first, and then obtain the crowd locations. However, the…

Multiview Detection

Improving Sequence-to-Sequence Learning via Optimal Transport

2019-01-18 · ICLR 2019 5 · Liqun Chen, Yizhe Zhang, Ruiyi Zhang, Chenyang Tao 외

Sequence-to-sequence models are commonly trained via maximum likelihood estimation (MLE). However, standard MLE training considers a word-level objective, predicting the next word given the previous ground-truth partial …

Abstractive Text SummarizationImage CaptioningMachine TranslationSentence+2