AI Paper Atlas

Research map / 3D vision / Depth and stereo

Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion

Massimiliano Viola, Kevin Qu, Nando Metzger, Bingxin Ke, Alexander Becker, Konrad Schindler, Anton Obukhov

ICCV 2025 · 3D vision › Depth and stereo · approach: Dense depth prediction and completion · 56 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 sparse-depth test-time guidance to a frozen pretrained Marigold depth estimatorMarigold · ScanNet zero-shotMAE: 0.083 -> 0.017 (Marigold + LS vs Marigold-DC)Improved
add 10-prediction median ensemble (ablation)Marigold-DC · NYU-Depth V2MAE: 0.057 -> 0.048Improved
use min-max initialization instead of least-squares for scale and shift (ablation)Marigold-DC · NYU-Depth V2 subsetMAE: 0.065 -> 0.055Improved
optimize depth latent directly instead of modifying the score function (ablation)Marigold-DC · NYU-Depth V2 subsetMAE: 0.058 -> 0.055Improved
increase DDIM denoising steps (ablation)Marigold-DC · NYU-Depth V2 subsetMAEImproved
increase learning rate for depth latent beyond 0.05 or decrease below (ablation)Marigold-DC · NYU-Depth V2 subsetMAEHurt
increase ensemble size beyond 10 (ablation)Marigold-DC · NYU-Depth V2 subsetMAENo clear effect
use Marigold-DC versus VPP4DC on denser VOID guidance and DDADMarigold-DC · DDAD front cameraMAE: 1.344 -> 2.364 (VPP4DC vs Marigold-DC); RMSE 6.781 -> 6.449Mixed
use Marigold-DC on very sparse guidance of 150 points versus propagation methodsMarigold-DC · VOID 150MAE: 0.492 -> 0.194 (NLSPN vs Marigold-DC)Improved

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