AI Paper Atlas

Research map / Video / Video generation

DepthSync: Diffusion Guidance-Based Depth Synchronization for Scale- and Geometry-Consistent Video Depth Estimation

Yue-Jiang Dong, Wang Zhao, Jiale Xu, Ying Shan, Song-Hai Zhang

ICCV 2025 · Video › Video generation · approach: Efficient video diffusion models · 2 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add scale guidance during denoising (without geometry guidance) (ablation)DepthCrafter · ScanNet first 35 scenes, 150 framesAbsRel: 0.174 -> 0.151Improved
add geometry guidance (without scale guidance) (ablation)DepthCrafter · ScanNet first 35 scenes, 150 framesMFC: 0.024 -> 0.018Improved
combine scale and geometry guidance (ablation)DepthCrafter · ScanNet first 35 scenes, 150 framesAbsRel: 0.174 -> 0.137Improved
apply regularization inside the denoising loop instead of post-optimization (ablation)DepthSync · ScanNet first 35 scenes, 150 framesAbsRel: 0.151 -> 0.137Improved
post geometry optimization alone (after denoising) (ablation)DepthCrafter · ScanNet first 35 scenes, 150 framesAbsRel: 0.174 -> 0.175No clear effect
start guidance earlier (last 5 steps instead of last 2) (ablation)DepthSync · ScanNet first 25 scenes, 150 framesAbsRel: 0.137 -> 0.146Hurt
apply guidance only in the last step (ablation)DepthSync · ScanNet first 25 scenes, 150 framesAbsRel: 0.137 -> 0.151Hurt
start guidance at third-to-last instead of second-to-last step (ablation)DepthSync · ScanNet first 25 scenes, 150 framesdelta1: 0.801 -> 0.803No clear effect
apply geometry guidance before scale guidance (ablation)DepthSync · ScanNet first 25 scenes, 150 framesAbsRel: 0.145 -> 0.137Improved
use all four geometry loss terms instead of any single one (ablation)Geometry guidance · ScanNet first 25 scenes, 150 framesAbsRel: 0.122 -> 0.108Improved
apply scale guidance throughout denoising instead of only at initializationDepthCrafter · Bonn (590 frames)delta1: 0.801 -> 0.929Improved
use lightweight scale-only guidance at penultimate step (Ours-S) (ablation)DepthSync · ScanNet (150 frames)AbsRel: 0.113 -> 0.128Mixed

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy