AI Paper Atlas

Research map / 3D vision / 3D generation

REPARO: Compositional 3D Assets Generation with Differentiable 3D Layout Alignment

Haonan Han, Rui Yang, Huan Liao, Jiankai Xing, Zunnan Xu, Xiaoming Yu, Junwei Zha, Xiu Li, Wanhua Li

ICCV 2025 · 3D vision › 3D generation · approach: Generative indoor scene synthesis · 35 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 optimal transport to RGB appearance loss (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)CLIP score: 0.800 -> 0.828Improved
add optimal transport to RGB appearance loss (ablation)REPARO (TripoSR) · GSO multi-object scenes (20)CLIP score: 0.774 -> 0.819Improved
add depth to RGBXY OT appearance loss (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)CLIP score: 0.828 -> 0.833Improved
add position and depth to RGB OT loss (ablation)REPARO (TripoSR) · GSO multi-object scenes (20)CLIP score: 0.819 -> 0.822No clear effect
add semantic loss L_s to appearance loss L_a (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)LPIPS: 0.233 -> 0.234No clear effect
use only semantic loss without appearance loss (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)CLIP score: 0.833 -> 0.809Hurt
add scale optimization to translation (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)CLIP score: 0.832 -> 0.833No clear effect
add rotation optimization to translation and scale (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)CLIP score: 0.833 -> 0.831Hurt
add rotation optimization to translation (ablation)REPARO (DreamGaussian) · GSO multi-object scenes (20)LPIPS: 0.232 -> 0.243Hurt
add rotation to translation and scale (ablation)REPARO (TripoSR) · GSO multi-object scenes (20)CLIP score: 0.822 -> 0.826Mixed
use TripoSR instead of DreamGaussian as 3D generatorREPARO · GSO multi-object scenes (20)LPIPS: 0.234 -> 0.216Improved
use ground-truth assets instead of generatedREPARO · GSO multi-object scenes (20)CLIP score: 0.822 -> 0.906Improved

Later papers that compared with this method

1 later accepted paper reports REPARO as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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