用核心集剪枝让NeRF训练快35%、模型小一半，精度损失极小。
Neural Pruning for 3D Scene Reconstruction: Efficient NeRF Acceleration
- 基于核心集选择关键样本，动态剪枝神经辐射场。
- 模型尺寸减半，训练速度提升35%，精度仅轻微下降。
- 适合资源受限场景下的高效3D重建应用。
神经辐射场（NeRF）近年来成为主流的3D重建方法，但其训练时间长，常需数日。本文研究神经剪枝作为优化手段，对比了均匀采样、基于重要性及核心集驱动的剪枝策略，以减少模型规模并加速训练。结果表明，核心集驱动的剪枝可实现50%的模型尺寸压缩和35%的训练速度提升，同时仅带来轻微精度损失。这些发现表明，剪枝是提升资源受限环境下NeRF效率的有效方法。
原文摘要 · Abstract (English)
Neural Radiance Fields (NeRF) have become a popular 3D reconstruction approach in recent years. While they produce high-quality results, they also demand lengthy training times, often spanning days. This paper studies neural pruning as a strategy to address these concerns. We compare pruning approaches, including uniform sampling, importance-based methods, and coreset-based techniques, to reduce the model size and speed up training. Our findings show that coreset-driven pruning can achieve a 50% reduction in model size and a 35% speedup in training, with only a slight decrease in accuracy. These results suggest that pruning can be an effective method for improving the efficiency of NeRF models in resource-limited settings.
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。