拡散モデル誘導による都市シーン再構成の汎用高品質化手法
Diffusion-guided Generalizable Enhancer for Urban Scene Reconstruction
都市シーンの3D再構成において、視点が大きくずれると画質が劣化する問題を、拡散モデルの生成的先験知識を活用して数分で修正する汎用的な手法GenReを提案した。
詳しい要約
1. どんなもの？
2. 先行研究と比べてどこがすごい？
3. 技術・手法の肝は？
4. どうやって有効だと検証した？
5. 議論はある？
6. 次に読むべき論文は？
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Henry Che, Jingkang Wang, Yun Chen, Ze Yang, Sivabalan Manivasagam, Raquel Urtasun
分類: cs.CV, cs.AI, cs.RO
原文アブストラクト
Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories, their quality degrades significantly under large viewpoint shifts, limiting the applicability for closed-loop simulation. Recent works have shown promising results in using diffusion models to enhance quality at these challenging viewpoints and distill improvements back into 3D representations. However, they often require costly per-scene optimization, and the distilled representations remain fragile and fail to generalize beyond limited synthesized views. To address these limitations, we propose GenRe, a novel diffusion-guided generalizable enhancer for urban scene reconstruction. GenRe takes as input any pretrained 3D Gaussian representation and fixes the deficiencies within a few minutes. By learning to distill generative priors across diverse scenes, GenRe produces robust and high-fidelity representation efficiently that generalizes reliably to challenging unseen viewpoints (e.g., lane change). Experiments show that GenRe outperforms existing methods in both quality and efficiency and benefits various downstream tasks, enabling robust and scalable sensor simulation for autonomous driving.
