AI Paper Atlas

Research map / 3D vision / 3D generation

DG3D: Generating High Quality 3D Textured Shapes by Learning to Discriminate Multi-Modal Diffusion-Renderings

Qi Zuo, Yafei Song, Jianfang Li, Lin Liu, Liefeng Bo

ICCV 2023 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 6 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 the diffusion-augmented module and multi-modal discriminators to GET3D-style generatorGET3D (IG) · ShapeNet CarFID-3D: 10.60 -> 6.09Improved
add multi-modal discriminators (RGB, alpha, patch) (ablation)DG3D · ShapeNet CarFID-3D: 9.23 -> 6.09Improved
add diffusion-augmented module (ablation)DG3D · ShapeNet CarFID-3D: 8.12 -> 6.09Improved
add diffusion-augmented module (ablation)DG3D · ShapeNet MotorbikeCOV-LFD (%): 71.42 -> 75.34Improved
add multi-modal discriminators (ablation)DG3D · ShapeNet ChairFID-3D: 21.07 -> 18.84Improved
apply DG3D on real scans versus GET3DDG3D · ScanHeadFID-3D: 43.29 -> 35.18Improved
use fixed-deviation gaussian filter on binary masks instead of adaptive diffusionGAN with binary mask discrimination · training stabilitymode collapseHurt
DG3D versus point-based/occupancy methods on geometry coverageDG3D · ShapeNet Chair and MotorbikeCOV-LFD (%): PointFlow 49.58 vs DG3D 74.80 (LFD); CD coverage 71.87 vs 73.65Mixed

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