AI Paper Atlas

Research map / 3D vision / 3D generation

Ultra3D: Efficient and High-Fidelity 3D Generation with Part Attention

Yiwen Chen, Zhihao Li, Yihao Luo, Yikai Wang, Zhang Hu, Le Li, Qin Li, Chi Zhang, Guosheng Lin

ECCV 2026 · 3D vision › 3D generation · approach: Score distillation for text-to-3D · 51 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
replace full attention in the second-stage DiT with Part Attention (ablation)Ultra3D · User study (b) full vs part attentionselection rate (%): 12.4% vs 8.9%, 78.7% no preferenceNo clear effect
use Part Attention instead of fixed 3D window attention (ablation)Ultra3D · User study (c) 3D window vs part attentionselection rate (%): 2.1% -> 63.7%Improved
use Part Self Attention instead of full attention (ablation)Ultra3D DiT · Efficiency vs full attentionspeedup: 6.7xImproved
use Part Cross Attention instead of full cross attention (ablation)Ultra3D DiT · Efficiency vs full attentionspeedup: 4.1xImproved
replace most DiT layers with Part Attention (ablation)Ultra3D DiT · Efficiency vs full attentiontraining and inference speedup: 3.1x training, 3.3x inferenceImproved
use Ultra3D with Part Attention instead of full attention pipeline (ablation)Ultra3D · Per-sample generation timeminutes per mesh: over 15 minutes -> 4 minutesImproved
compare Ultra3D against Direct3D-S2 and Commercial Model AUltra3D · User study (a) vs other methodsselection rate (%): 7.2% and 24.3% -> 68.5%Improved
vary number of part groups at inference away from the 8 used in training (ablation)Ultra3D · Qualitative generation qualityvisual qualityNo clear effect
increase sparse voxel resolution used in attention and drop downsampling (ablation)Ultra3D · Qualitative generation qualityvisual qualityImproved

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