AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysis

Bingxin Ke, Kevin Qu, Tianfu Wang, Nando Metzger, Shengyu Huang, Bo Li, Anton Obukhov, Konrad Schindler B

TPAMI 2025 · Image generation › Text-to-image diffusion · approach: Text-driven synthesis and semantic guidance · 78 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 Virtual KITTI to HyperSim training data (ablation)Marigold-Depth · KITTI (depth ablation)AbsRel: 13.7 -> 11.3Improved
add Virtual KITTI to HyperSim training data (ablation)Marigold-Depth · NYUv2 (depth ablation)AbsRel: 5.7 -> 5.6Improved
add HyperSim to Virtual KITTI training data (ablation)Marigold-Depth · NYUv2 (depth ablation)AbsRel: 13.9 -> 5.6Improved
use trailing DDIM timesteps instead of leading (ablation)Marigold-Depth · depth benchmarksNFE needed: 50 steps -> 1 stepImproved
increase test-time ensemble from 1 to 10 predictions (ablation)Marigold-Depth · NYUv2AbsRel: ~8%Improved
increase test-time ensemble from 1 to 20 predictions (ablation)Marigold-Depth · NYUv2AbsRel: ~9.5%Improved
use model v1.1 with 10x4 ensemble and steps instead of 1x1 (ablation)Marigold-Depth v1.1 · NYUv2AbsRel: 5.9 -> 5.5Improved
run in fp16Marigold v1.1 (1x1) · inference timetime (s): 0.568 -> 0.274Improved
use TAESD VAE with fp16Marigold v1.1 (1x1) · inference timetime (s): 0.274 -> 0.082Improved
use TAESD VAE with fp16Marigold v1.1 (1x1) · KITTIAbsRel: 11.0 -> 12.4Hurt
increase denoising steps from 1 to 4 (ablation)Marigold-Normals · normals benchmarksaccuracyImproved
increase ensemble beyond 10 predictions (ablation)Marigold-Normals · ScanNet and DIODEaccuracyNo clear effect

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