CVAug 4, 2018

T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks

arXiv:1808.01454v1201 citations
Originality Highly original
AI Analysis

This addresses the data acquisition problem for researchers and practitioners in computer vision, offering an incremental improvement by using synthetic data to reduce reliance on costly real datasets.

The paper tackles the difficulty of acquiring real image-depth pairs for single-image depth estimation by proposing T2Net, a framework trained on synthetic image-depth pairs and unpaired real images, which achieves results surpassing early deep-learning methods that use real paired data.

Current methods for single-image depth estimation use training datasets with real image-depth pairs or stereo pairs, which are not easy to acquire. We propose a framework, trained on synthetic image-depth pairs and unpaired real images, that comprises an image translation network for enhancing realism of input images, followed by a depth prediction network. A key idea is having the first network act as a wide-spectrum input translator, taking in either synthetic or real images, and ideally producing minimally modified realistic images. This is done via a reconstruction loss when the training input is real, and GAN loss when synthetic, removing the need for heuristic self-regularization. The second network is trained on a task loss for synthetic image-depth pairs, with extra GAN loss to unify real and synthetic feature distributions. Importantly, the framework can be trained end-to-end, leading to good results, even surpassing early deep-learning methods that use real paired data.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes