AI Paper Atlas

Research map / 3D vision / 3D generation

Learning Pseudo 3D Guidance for View-consistent Texturing with 2D Diffusion

Kehan Li, Yanbo Fan, Yang Wu, Zhongqian Sun, Wei Yang, Xiangyang Ji, Li Yuan, Jie Chen

ECCV 2024 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 4 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 pseudo 3D semantic guidance to multi-view texture generation (ablation)P3G texturing pipeline · Objaverse 410 meshesCLIP Variance: 10.20 -> 8.13Improved
add pseudo 3D semantic guidance (ablation)P3G texturing pipeline · Objaverse 410 meshesCLIP-IQA: 38.14 -> 46.17Improved
add pseudo 3D semantic guidance (ablation)P3G texturing pipeline · Objaverse 410 meshesFID: 60.1 -> 58.0Improved
add pseudo 3D semantic guidance (ablation)P3G texturing pipeline · Objaverse 410 meshesCLIP Score: 25.07 -> 25.53Improved
use dynamic area-maximizing view selection instead of sequential views (ablation)P3G texturing pipeline · regular and irregular shapesaverage face-view cosine over iterationsImproved
P3G versus TEXTure on text matchingP3G · Objaverse 410 meshesCLIP Score: 25.66 -> 25.53No clear effect
P3G versus TEXTure in a user studyP3G · User studyInconsistency: 23.63 -> 15.55Improved

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