论文标题
使用Tri-Cycle gan无监督对现实世界深度图像的增强
Unsupervised Enhancement of Real-World Depth Images Using Tri-Cycle GAN
论文作者
论文摘要
低质量深度对计算机视觉算法构成了巨大的挑战。在这项工作中，我们旨在增强低成本传感器获得的高度退化的现实深度图像，为此，分析噪声模型无法使用。在没有干净的地面真相的情况下，我们将任务作为使用两个未配对的训练集代表的低质量传感器域和高质量传感器域之间的无监督域翻译。我们在此任务中采用了高度成功的周期训练，但在这种情况下它的性能很差。识别故障的来源，我们对框架进行了一些修改，包括较大的发电机架构，考虑到缺失像素的深度特异性损失以及一种新颖的三循环损失，该损失促进了信息预言，同时解决了域之间的不对称。我们表明，最终的框架在视觉和定量上都大大改进了原始循环gan，将其适用性扩展到了更具挑战性和不对称的翻译任务。
Low quality depth poses a considerable challenge to computer vision algorithms. In this work we aim to enhance highly degraded, real-world depth images acquired by a low-cost sensor, for which an analytical noise model is unavailable. In the absence of clean ground-truth, we approach the task as an unsupervised domain-translation between the low-quality sensor domain and a high-quality sensor domain, represented using two unpaired training sets. We employ the highly-successful Cycle-GAN to this task, but find it to perform poorly in this case. Identifying the sources of the failure, we introduce several modifications to the framework, including a larger generator architecture, depth-specific losses that take into account missing pixels, and a novel Tri-Cycle loss which promotes information-preservation while addressing the asymmetry between the domains. We show that the resulting framework dramatically improves over the original Cycle-GAN both visually and quantitatively, extending its applicability to more challenging and asymmetric translation tasks.
