AI Paper Atlas

Research map / 3D vision / 3D generation

From Sparse to Dense: Multi-View GRPO for Flow Models via Augmented Condition Space

Jiazi Bu, Pengyang Ling, Yujie Zhou, Yibin Wang, Yuhang Zang, Tianyi Wei, Xiaohang Zhan, Jiaqi Wang, Tong Wu, Xingang Pan, Dahua Lin

ECCV 2026 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 3 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 augmented multi-view conditions (K=12, VLM enhancer) (ablation)Flow-GRPO-Fast · HPD eval (HPS-v3 reward training)HPS-v3: 0.149 -> 0.155Improved
add augmented multi-view conditions (K=12) (ablation)Flow-GRPO-Fast · HPD eval (HPS-v3 reward training)ImageReward: 1.152 -> 1.193Improved
add augmented multi-view conditions (K=12) (ablation)Flow-GRPO-Fast · HPD eval (HPS-v3 reward training)CLIP score: 0.378 -> 0.370Hurt
increase K from 6 to 12 (ablation)MV-GRPO · HPD eval (HPS-v3 reward training)HPS-v3: 0.154 -> 0.155Improved
derive conditions from distinct SDE samples (ablation)MV-GRPO · HPD eval (HPS-v3 reward training)HPS-v3: 0.153 -> 0.155Improved
add multi-perspective VLM prompt set (ablation)MV-GRPO · HPD eval (HPS-v3 reward training)HPS-v3: 0.152 -> 0.155Improved
use 8B instead of 2B VLM enhancer (ablation)MV-GRPO · HPD eval (HPS-v3 reward training)HPS-v3: 0.153 -> 0.155Improved
use online VLM instead of offline LLM enhancerMV-GRPO · HPD eval (UnifiedReward-v2 reward training)ImageReward: 1.118 -> 1.187Improved
MV-GRPO vs best baseline on HPS-v3 rewardMV-GRPO (VLM) · HPD eval (HPS-v3 reward training)HPS-v3: 0.150 -> 0.155 (TempFlow-GRPO)Improved
MV-GRPO vs baselines on CLIP scoreMV-GRPO (VLM) · HPD eval (HPS-v3 reward training)CLIP score: 0.380 -> 0.370 (Flow-GRPO)Hurt
integrate MV-GRPO into DanceGRPO-FastDanceGRPO-Fast · HPD eval (HPS-v3 reward training)HPS-v3: 0.149 -> 0.154Improved
use condition augmentation instead of data augmentationFlow-GRPO-Fast · iteration timeiteration time (s): 1931.15 -> 191.95Improved

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