Papers › Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

Jasmine: Harnessing Diffusion Prior for Self-supervised Depth Estimation

20 Mar 2025arXiv:2503.15905archive 2025-07-28

Jiyuan Wang, Chunyu Lin, Cheng Guan, Lang Nie, Jing He, Haodong Li, Kang Liao, Yao Zhao

In this paper, we propose Jasmine, the first Stable Diffusion (SD)-based self-supervised framework for monocular depth estimation, which effectively harnesses SD's visual priors to enhance the sharpness and generalization of unsupervised prediction. Previous SD-based methods are all supervised since adapting diffusion models for dense prediction requires high-precision supervision. In contrast, self-supervised reprojection suffers from inherent challenges (e.g., occlusions, texture-less regions, illumination variance), and the predictions exhibit blurs and artifacts that severely compromise SD's latent priors. To resolve this, we construct a novel surrogate task of hybrid image reconstruction. Without any additional supervision, it preserves the detail priors of SD models by reconstructing the images themselves while preventing depth estimation from degradation. Furthermore, to address the inherent misalignment between SD's scale and shift invariant estimation and self-supervised scale-invariant depth estimation, we build the Scale-Shift GRU. It not only bridges this distribution gap but also isolates the fine-grained texture of SD output against the interference of reprojection loss. Extensive experiments demonstrate that Jasmine achieves SoTA performance on the KITTI benchmark and exhibits superior zero-shot generalization across multiple datasets.

PaperPDF

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

Depth EstimationImage ReconstructionMonocular Depth EstimationZero-shot Generalization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Delta < 1.25 0.919 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Delta < 1.25^2 0.972 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Delta < 1.25^3 0.986 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Mono O #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine RMSE 3.944 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine RMSE log 0.161 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Resolution 1024x320 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine Sq Rel 0.581 #4 of 55 Archive leaderboard report
Monocular Depth Estimation KITTI Eigen split unsupervised Jasmine absolute relative error 0.09 #4 of 55 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

DiffusionGRU

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