CUDA-Accelerated RF-NeRF Benjamin J Gilbert College of the Mainland Robotic Process AutomationDownload
We present a CUDA-accelerated renderer for RF conditioned NeRF with GPU kernels for ray generation, stratified sampling, and volumetric integration. A small benchmark
sweeps samples and chunk sizes, logging PSNR/SSIM vs. latency;
JSON→LATEX keeps tables and plots reproducible.
