AI Paper Atlas

Research map / 3D vision / 3D generation

GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Xiao Fu, Wei Yin, Mu Hu, Kaixuan Wang, Yuexin Ma, Ping Tan, Shaojie Shen, Dahua Lin, Xiaoxiao Long

ECCV 2024 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 156 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 cross-domain geometry switcher and cross-domain attention for joint depth and normal (ablation)GeoWizard · Ablation validation sets (overall)Geometric consistency (GC): 18.1 -> 16.2Improved
use one joint model instead of separate depth and normal models (ablation)GeoWizard · Ablation validation sets (overall)AbsRel: 8.5 -> 6.7Improved
add scene distribution decoupler (ablation)GeoWizard · Ablation validation sets (overall)AbsRel: 7.5 -> 6.7Improved
add scene distribution decoupler (ablation)GeoWizard · Object domain (OmniObject3D samples)AbsRel: 3.7 -> 3.5No clear effect
use geometry switcher instead of shared geometry embedding (ablation)GeoWizard · Ablation validation sets (overall)AbsRel: 7.2 -> 6.7Improved
use wrong domain indicator at test time (indoor test with outdoor indicator) (ablation)GeoWizard · Indoor ablation setGeometric consistency (GC): 14.7 -> 14.4Mixed
use wrong domain indicator at test time (object indicator on indoor) (ablation)GeoWizard · Indoor ablation setAbsRel: 5.5 -> 6.4Hurt
use GeoWizard depth/normal as guidance for MonoSDF reconstruction instead of Omnidata v2 or DSINEMonoSDF · ScanNet (4 scenes)F-score: 74.7 -> 75.1Improved
generative diffusion-prior model versus discriminative DepthAnything trained on 63.5M imagesGeoWizard · NYUv2 (zero-shot depth)AbsRel: 4.3 -> 5.2Hurt

Later papers that compared with this method

5 later accepted papers report GeoWizard as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

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