AI Paper Atlas

Research map / Image generation / Text-to-image diffusion

LEGO-Maker: A Semantic-Driven Algorithm for Text-to-3D Generation

Yifei Zhang, Lei Chen

ICCV 2025 · Image generation › Text-to-image diffusion · approach: Layout-to-image control · 1 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 texture enhancement (ablation)LEGO-Maker (TRELLIS) · T3Bench (Multiple Objects), ablationQuality: 51.25 -> 52.90Improved
add texture enhancement (ablation)LEGO-Maker (TRELLIS) · T3Bench (Multiple Objects), ablationConsistency: 42.89 -> 43.60Improved
add texture enhancement (ablation)LEGO-Maker (SPAR3D) · T3Bench (Multiple Objects), ablationQuality: 49.47 -> 51.17Improved
add diffusion retraining (ablation)LEGO-Maker (TRELLIS) · T3Bench (Multiple Objects), ablationQuality: 49.04 -> 52.90Improved
add diffusion retraining (ablation)LEGO-Maker (TRELLIS) · T3Bench (Multiple Objects), ablationConsistency: 39.58 -> 43.60Improved
add diffusion retraining (ablation)LEGO-Maker (SPAR3D) · T3Bench (Multiple Objects), ablationQuality: 48.26 -> 51.17Improved
add both texture enhancement and diffusion retraining (ablation)LEGO-Maker (TRELLIS) · T3Bench (Multiple Objects), ablationQuality: 48.23 -> 52.90Improved
add both texture enhancement and diffusion retraining (ablation)LEGO-Maker (SPAR3D) · T3Bench (Multiple Objects), ablationConsistency: 36.89 -> 41.87Improved
use TRELLIS instead of SPAR3D as image-to-3D generator (ablation)LEGO-Maker · T3Bench (Multiple Objects), ablationQuality: 51.17 -> 52.90No clear effect
use LEGO-Maker instead of Meshy 2.0Meshy 2.0 · T3Bench (Multiple Objects)Quality: 49.33 -> 52.90Improved
use LEGO-Maker instead of Hun Yuan 2.0Hun Yuan 2.0 · Toys4KFD_dinov2: 249.75 -> 210.23Improved
use LEGO-Maker instead of Hun Yuan 2.0 for speedHun Yuan 2.0 · Toys4KInference time: 1 min -> 3 minHurt

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