Papers › T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
T2Net: Synthetic-to-Realistic Translation for Solving Single-Image Depth Estimation Tasks
Chuanxia Zheng, Tat-Jen Cham, Jianfei Cai
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.
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.
Code Syntology ran Syntology
Not run by Syntology. Nothing on this page verifies that the listed code works.
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Depth Estimation | DCM | T2Net | Abs Rel | 0.351 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | DCM | T2Net | RMSE | 1.117 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | DCM | T2Net | RMSE log | 0.415 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | DCM | T2Net | Sq Rel | 0.416 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | eBDtheque | T2Net | Abs Rel | 0.491 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | eBDtheque | T2Net | RMSE | 1.459 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | eBDtheque | T2Net | RMSE log | 0.777 | #3 of 3 | Archive leaderboard | report |
| Depth Estimation | eBDtheque | T2Net | Sq Rel | 0.555 | #3 of 3 | Archive leaderboard | report |
| Unsupervised Domain Adaptation | virtual KITTI to KITTI (MDE) | T2Net | RMSE | 4.674 | #3 of 4 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
Methods
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections