Instant on-device Neural Radiance Fields (NeRFs) are in growing demand for unleashing the promise of immersive AR/VR experiences, but are still limited by their prohibitive training time. Our profiling analysis reveals a memory-bound inefficiency in NeRF training. To tackle this inefficiency, near-memory processing (NMP) promises to be an effective solution, but also faces challenges due to the unique workloads of NeRFs, including the random hash table lookup, random point processing sequence, and heterogeneous bottleneck steps. Therefore, we propose the first NMP framework, Instant-NeRF, dedicated to enabling instant on-device NeRF training. Experiments on eight datasets consistently validate the effectiveness of Instant-NeRF.

翻译：即时设备端神经辐射场（NeRF）技术在实现沉浸式增强现实/虚拟现实（AR/VR）体验方面需求日益增长，但其训练时间过长这一瓶颈仍限制其发展。我们的性能分析表明，NeRF训练存在受内存限制的低效问题。为克服这一低效性，近存处理（Near-Memory Processing, NMP）有望成为有效解决方案，但NeRF独特的工作负载（包括随机哈希表查找、随机点处理序列及异构瓶颈步骤）也为其带来挑战。为此，我们提出首个专用于实现即时设备端NeRF训练的NMP框架——Instant-NeRF。在八个数据集上的实验一致验证了Instant-NeRF的有效性。