AI Paper Atlas

Research map / 3D vision / 3D generation

Stroke3D: Lifting 2D strokes into rigged 3D model via latent diffusion models

Ruisi Zhao, Haoren Zheng, Zongxin Yang, Hehe Fan, Yi Yang

ICLR 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 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 TextuRig data (ablation)SKDream · skeleton-to-meshSKA score Mean_Inst: 80.43 -> 82.37Improved
add TextuRig data (ablation)SKDream · skeleton-to-meshSKA score Mean_Class: 74.38 -> 76.84Improved
add SKA-DPO (ablation)SKDream · skeleton-to-meshSKA score Mean_Inst: 80.43 -> 85.57Improved
add SKA-DPO on top of TextuRig (ablation)SKDream + TextuRig · skeleton-to-meshSKA score Mean_Inst: 82.37 -> 87.83Improved
add SKA-DPO on top of TextuRig (ablation)SKDream + TextuRig · skeleton-to-meshSKA score Mean_Class: 76.84 -> 84.36Improved
use preference margin 0.10 instead of 0.05 (ablation)SKA-DPO · skeleton-to-meshSKA score Mean_Inst: 86.95 -> 87.83Improved
use preference margin 0.10 instead of 0.20 (ablation)SKA-DPO · skeleton-to-meshSKA score Mean_Inst: 86.96 -> 87.83Improved
use preference margin 0.15 instead of 0.10 (ablation)SKA-DPO · skeleton-to-meshSKA score Mean_Inst: 87.83 -> 87.84No clear effect
add rotational alignment of dataset (ablation)Sk-DiT · skeleton generationCD-J2J (All): 0.0493 -> 0.0475Improved
add descriptive and viewpoint tags (ablation)Sk-DiT · skeleton generationCD-J2J (All): 0.0524 -> 0.0475Improved
use full training data instead of reduced subset (ablation)Sk-DiT · skeleton generationCD-J2J (All): 0.0544 -> 0.0475Improved
add 2D stroke structural condition Jxy (ablation)Sk-DiT · overfitting on 1 or 5 samplestraining lossImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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