CPU & GPU with Zero Hassle<p>Built with NVIDIA Warp, the same code runs seamlessly on both CPU and GPU — no need to deal with CUDA setup, driver issues, or device-specific kernels. Just flip one config line.<p>Learn Modern Graphics the Easy Way<p>Explore core concepts in differentiable rendering and parallel graphics programming — no need for expensive GPUs or thousands of lines of boilerplate.<p>Minimalist & Educational<p>This isn’t another massive codebase. It’s a clean, hackable implementation built for clarity — perfect for study, prototyping, or teaching yourself how Gaussian Splatting works.
Thanks for sharing! I hope a detailed, line-by-line explanation of the backward pass can be added. I previously tried deriving it by hand but couldn’t get it right. I’ll need to revisit it again later.