用专家混合加速坐标编码，实现大规模场景高效定位与高清渲染
MACE: Mixture-of-Experts Accelerated Coordinate Encoding for Large-Scale Scene Localization and Rendering
- 引入门控网络选择子网络，推理时仅激活一个专家，降低计算开销
- 在剑桥数据集上仅需10分钟训练即可达成高质量渲染效果
- 无需辅助损失的负载均衡策略，提升大场景定位精度
大规模场景中的高效定位与高质量渲染仍面临计算成本高的挑战。尽管场景坐标回归（SCR）方法在小规模场景中表现良好，但在扩展到大规模场景时受限于单个网络的容量。为此，我们提出基于专家混合的加速坐标编码方法（MACE），实现大规模场景下的高效定位与高质量渲染。受大型模型中专家混合（MOE）优异性能的启发，我们引入门控网络隐式分类并选择子网络，确保每次推理仅激活一个子网络。此外，我们提出无辅助损失的负载均衡（ALF-LB）策略，提升大场景定位精度。该框架在显著降低计算成本的同时保持更高精度，为大规模场景应用提供高效解决方案。在剑桥测试集上的额外实验表明，本方法仅需10分钟训练即可实现高质量渲染。
原文摘要 · Abstract (English)
Efficient localization and high-quality rendering in large-scale scenes remain a significant challenge due to the computational cost involved. While Scene Coordinate Regression (SCR) methods perform well in small-scale localization, they are limited by the capacity of a single network when extended to large-scale scenes. To address these challenges, we propose the Mixed Expert-based Accelerated Coordinate Encoding method (MACE), which enables efficient localization and high-quality rendering in large-scale scenes. Inspired by the remarkable capabilities of MOE in large model domains, we introduce a gating network to implicitly classify and select sub-networks, ensuring that only a single sub-network is activated during each inference. Furtheremore, we present Auxiliary-Loss-Free Load Balancing(ALF-LB) strategy to enhance the localization accuracy on large-scale scene. Our framework provides a significant reduction in costs while maintaining higher precision, offering an efficient solution for large-scale scene applications. Additional experiments on the Cambridge test set demonstrate that our method achieves high-quality rendering results with merely 10 minutes of training.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。