当前位置: X-MOL 学术J. Electr. Eng. Technol. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
A Generative Adversarial Network to Denoise Depth Maps for Quality Improvement of DIBR-Synthesized Stereoscopic Images
Journal of Electrical Engineering & Technology ( IF 1.6 ) Pub Date : 2021-04-07 , DOI: 10.1007/s42835-021-00728-2
Chuang Zhang , Xian-wen Sun , Jiawei Xu , Xiao-yu Huang , Gui-yue Yu , Seop Hyeong Park

Depth map quality is an important factor that affects the quality of synthesized stereoscopic images in stereoscopic visual communication systems using the depth image-based rendering (DIBR) technique. This paper proposes a method using a generative adversarial network (GAN) to denoise depth maps corrupted by several types of distortion. The generative network of the proposed GAN builds on convolutional layers, residual layers, and transposed convolutional layers with symmetric skip connections. The discriminative network of the proposed GAN is designed as a convolutional neural network. The generative network for denoising depth maps is trained with cropped depth maps where distortion is applied. Objective and subjective assessment of denoised depth maps and DIBR-synthesized stereoscopic images demonstrate that the proposed GAN effectively reduces the distortion in the depth maps and improves the quality of DIBR-synthesized stereoscopic images.



中文翻译:

用于对深度图进行降噪的生成对抗网络,以提高DIBR合成的立体图像的质量

深度图质量是影响使用基于深度图像的渲染(DIBR)技术的立体视觉通信系统中合成立体图像质量的重要因素。本文提出了一种使用生成对抗网络(GAN)来对因几种类型的失真而损坏的深度图进行去噪的方法。所提出的GAN的生成网络建立在具有对称跳过连接的卷积层,残差层和转置的卷积层上。提出的GAN的判别网络被设计为卷积神经网络。去噪深度图的生成网络使用裁剪后的深度图(其中应用了失真)进行训练。

更新日期:2021-04-08
down
wechat
bug