paper-with-me

Papers

Unpaired Single-Image Depth Synthesis with cycle-consistent Wasserstein GANs

2021-03-31 · Christoph Angermann, Adéla Moravová, Markus Haltmeier, Steinbjörn Jónsson, Christian Laubichler

Real-time estimation of actual environment depth is an essential module for various autonomous system tasks such as localization, obstacle detection and pose estimation. During the last decade of machine learning, extensive deployment of deep learning methods to computer vision tasks yielded successful approaches for realistic depth synthesis out of a simple RGB modality. While most of these models rest on paired depth data or availability of video sequences and stereo images, there is a lack of methods facing single-image depth synthesis in an unsupervised manner. Therefore, in this study, latest advancements in the field of generative neural networks are leveraged to fully unsupervised single-image depth synthesis. To be more exact, two cycle-consistent generators for RGB-to-depth and depth-to-RGB transfer are implemented and simultaneously optimized using the Wasserstein-1 distance. To ensure plausibility of the proposed method, we apply the models to a self acquised industrial data set as well as to the renown NYU Depth v2 data set, which allows comparison with existing approaches. The observed success in this study suggests high potential for unpaired single-image depth estimation in real world applications.

📄 PDF Abstract BibTeX arXiv:2103.16938

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationPose Estimation

Similar Papers 제목 키워드 기반

Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN

2018-09-12 · Heran Yang, Jian Sun, Aaron Carass, Can Zhao 외

The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between the…

Image GenerationPosition

Self-Augmented Unpaired Image Dehazing via Density and Depth Decomposition

2022-01-01 · CVPR 2022 1 · Yang Yang, Chaoyue Wang, Risheng Liu, Lin Zhang 외

To overcome the overfitting issue of dehazing models trained on synthetic hazy-clean image pairs, many recent methods attempted to improve models' generalization ability by training on unpaired data. Most of them sim…

Image Dehazing

DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data

2022-11-02 · Jiayuan Wang, Q. M. Jonathan Wu, Farhad Pourpanah

Magnetic resonance (MR) and computer tomography (CT) images are two typical types of medical images that provide mutually-complementary information for accurate clinical diagnosis and treatment. However, obtaining both i…

Image GenerationSSIM

Cross-modality image synthesis from unpaired data using CycleGAN: Effects of gradient consistency loss and training data size

2018-03-18 · Yuta Hiasa, Yoshito Otake, Masaki Takao, Takumi Matsuoka 외

CT is commonly used in orthopedic procedures. MRI is used along with CT to identify muscle structures and diagnose osteonecrosis due to its superior soft tissue contrast. However, MRI has poor contrast for bone structure…

Image Generation

Unsupervised Single Image Underwater Depth Estimation

2019-05-25 · Honey Gupta, Kaushik Mitra

Depth estimation from a single underwater image is one of the most challenging problems and is highly ill-posed. Due to the absence of large generalized underwater depth datasets and the difficulty in obtaining ground tr…

Depth Estimation