Papers › Monocular Depth Estimation using Diffusion Models
Monocular Depth Estimation using Diffusion Models
Saurabh Saxena, Abhishek Kar, Mohammad Norouzi, David J. Fleet
We formulate monocular depth estimation using denoising diffusion models, inspired by their recent successes in high fidelity image generation. To that end, we introduce innovations to address problems arising due to noisy, incomplete depth maps in training data, including step-unrolled denoising diffusion, an L₁ loss, and depth infilling during training. To cope with the limited availability of data for supervised training, we leverage pre-training on self-supervised image-to-image translation tasks. Despite the simplicity of the approach, with a generic loss and architecture, our DepthGen model achieves SOTA performance on the indoor NYU dataset, and near SOTA results on the outdoor KITTI dataset. Further, with a multimodal posterior, DepthGen naturally represents depth ambiguity (e.g., from transparent surfaces), and its zero-shot performance combined with depth imputation, enable a simple but effective text-to-3D pipeline. Project page: https://depth-gen.github.io
In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.
Code
No code repository is listed for this paper in the archive or in Syntology's graph.
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 |
|---|---|---|---|---|---|---|---|
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | Delta < 1.25 | 0.946 | #25 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | Delta < 1.25^2 | 0.987 | #25 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | Delta < 1.25^3 | 0.996 | #25 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | RMSE | 0.314 | #25 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | absolute relative error | 0.074 | #25 of 85 | Archive leaderboard | report |
| Monocular Depth Estimation | NYU-Depth V2 | DepthGen | log 10 | 0.032 | #25 of 85 | 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