Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
Instant Neural Graphics Primitives with a Multiresolution Hash Encoding
复制标题
DOI：
10.1145/3528223.3530127
复制
发表时间：
2022-07-01
影响因子：
6.2
通讯作者：
Keller, Alexander
中科院分区：
文献类型：
--
作者：
Mueller, Thomas;Evans, Alex;Keller, Alexander
由完全连接的神经网络参数化的神经图形基元的训练和评估成本可能很高。我们通过一种多功能的新输入编码来降低成本，该编码允许使用更小的网络而不牺牲质量，从而显着减少浮点数和内存访问操作的数量：一个小型神经网络由可训练特征向量的多分辨率哈希表增强，其值通过随机梯度下降进行优化。多分辨率结构允许网络消除哈希冲突的歧义，从而形成一个简单的架构，在现代GPU上并行化是微不足道的。我们通过使用完全融合的CUDA内核实现整个系统来利用这种并行性，重点是最大限度地减少浪费的带宽和计算操作。我们实现了几个数量级的综合加速，能够在几秒钟内训练高质量的神经图形基元，并以1920x1080的分辨率在几十毫秒内渲染。
Neural graphics primitives, parameterized by fully connected neural networks, can be costly to train and evaluate. We reduce this cost with a versatile new input encoding that permits the use of a smaller network without sacrificing quality, thus significantly reducing the number of floating point and memory access operations: a small neural network is augmented by a multiresolution hash table of trainable feature vectors whose values are optimized through stochastic gradient descent. The multiresolution structure allows the network to disambiguate hash collisions, making for a simple architecture that is trivial to parallelize on modern GPUs. We leverage this parallelism by implementing the whole system using fully-fused CUDA kernels with a focus on minimizing wasted bandwidth and compute operations. We achieve a combined speedup of several orders of magnitude, enabling training of high-quality neural graphics primitives in a matter of seconds, and rendering in tens of milliseconds at a resolution of 1920x1080.