基于持续神经图形基元的增量多场景建模
Incremental Multi-Scene Modeling via Continual Neural Graphics Primitives
AI总结：
针对NeRF多场景建模的可扩展性问题，提出持续学习框架C-NGP，采用生成回放将多个场景增量集成到单个神经辐射场，在不增加参数的情况下实现高质量渲染，Real-LLFF数据集8个场景联合建模PSNR仅降2.2%。
摘要：
神经辐射场（NeRF）彻底改变了3D场景新视角的逼真渲染。尽管NeRF作为3D资源日益流行且高效，但由于每个场景需要单独模型以及多场景训练时间累积增加，其面临可扩展性挑战。将多个3D场景增量编码到单个NeRF模型的潜力在很大程度上仍未被探索。为此，我们提出持续神经图形基元（C-NGP），这是一种新颖的持续学习框架，可将多个场景增量集成到单个神经辐射场中。C-NGP采用生成回放方法，无需访问旧数据即可适应新场景。我们证明C-NGP能在不增加参数数量的情况下容纳多个场景，在合成和真实数据集上生成高质量新视角渲染。值得注意的是，C-NGP将Real-LLFF数据集中的全部8个场景一起建模，与独立建模每个场景的原始NeRF相比，PSNR仅下降2.2%。此外，C-NGP允许在同一网络中进行多种风格编辑。
英文摘要：
Neural radiance fields (NeRF) have revolutionized photorealistic rendering of novel views for 3D scenes. Despite their growing popularity and efficiency as 3D resources, NeRFs face scalability challenges due to the need for separate models per scene and the cumulative increase in training time for multiple scenes. The potential for incrementally encoding multiple 3D scenes into a single NeRF model remains largely unexplored. To address this, we introduce Continual-Neural Graphics Primitives (C-NGP), a novel continual learning framework that integrates multiple scenes incrementally into a single neural radiance field. Using a generative replay approach, C-NGP adapts to new scenes without requiring access to old data. We demonstrate that C-NGP can accommodate multiple scenes without increasing the parameter count, producing high-quality novel-view renderings on synthetic and real datasets. Notably, C-NGP models all $8$ scenes from the Real-LLFF dataset together, with only a $2.2\%$ drop in PSNR compared to vanilla NeRF, which models each scene independently. Further, C-NGP allows multiple style edits in the same network.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
