AI Paper Atlas

Research map / 3D vision / 3D generation

Think-Then-Generate: Structural Chain-of-Thought Reasoning for Consistent 3D Generation

Xinyue Liu, Jin Liu, Hongbo Wang, Ran He, Huaibo Huang

CVPR 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D

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 3DBlueprint-CoT (staged prompt planning) (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/32: 22.76 -> 24.65Improved
add 3DBlueprint-CoT (staged prompt planning) (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/16: 26.86 -> 29.15Improved
add 3DRefine-CoT (reflection, correction, MLLM voting) (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/32: 23.56 -> 24.65Improved
add 3DRefine-CoT (reflection, correction, MLLM voting) (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/16: 28.87 -> 29.15Improved
add Cross-view Semantic Appearance Alignment (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/32: 23.97 -> 24.65Improved
add Cross-view Semantic Appearance Alignment (ablation)Thoughtful3D on GaussianDreamer · Text-to-3D (100 prompts)CLIP Score L/14: 29.42 -> 30.39Improved
add 3DBlueprint-CoT alone relative to baseline (w/o A vs Baseline) (ablation)GaussianDreamer · Text-to-3D (100 prompts)CLIP Score B/16: 26.71 -> 26.86No clear effect
add Thoughtful3D to Fantasia3DFantasia3D · Text-to-3D (100 prompts)CLIP Score B/32: 16.71 -> 23.33Improved
add Thoughtful3D to Magic3DMagic3D · Text-to-3D (100 prompts)CLIP Score B/32: 16.28 -> 19.64Improved
add Thoughtful3D to DreamFusion-IFDreamFusion-IF · Text-to-3D (100 prompts)CLIP Score L/14: 23.22 -> 28.67Improved
add Thoughtful3D to Zero123Zero123 · Image-to-3D (50 objects)Volume IoU: 0.3203 -> 0.3714Improved
add Thoughtful3D to Wonder3DWonder3D · Image-to-3D (50 objects)SSIM: 0.8201 -> 0.8234Improved

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