13 items across game development
13 results
arXiv cs.GR details CuACD, a fully GPU-resident approximate convex decomposition pipeline that turns triangle meshes into convex parts much faster. The authors say it can cut preprocessing from tens...
A new Gaussian splatting pipeline swaps bulky spherical harmonics for compact neural appearance codes, cutting per-primitive appearance storage from 192 bytes to 28. The result is a 1.3× faster...
Disney Research Studios has introduced RaNA, a ragged neighborhood attention operator for denoising deep Monte Carlo renders. The method powers RaNAD, the first spatiotemporal neural denoiser for...
A CUDA-based finite-model checker pushed 1.63×10^14 modal formula evaluations through one H100 in 45 minutes, while verifying every emitted countermodel certificate. The interesting part for...
A CUDA+MPI framework aims to make multi-GPU ray-style workloads easier to scale across nodes without hand-rolling the plumbing. For graphics and simulation teams, the practical win is less time spent...
A new GPU-oriented IPC simulation framework, YASPS, tries to solve a real pain point: extending contact-rich solvers without rewriting a pile of specialized kernels. It bakes relational structure...
3D Gaussian Splatting gets a practical upgrade here: the paper swaps symmetric blobs for skew Gaussians to better fit sharp edges, transparency, and uneven detail. For graphics teams, the interesting...
CuRast introduces a significant leap in software rasterization, enabling the rendering of billions of triangles with impressive speed. This advancement is particularly relevant for graphics...
With your permission, GameDev.net uses analytics cookies to understand how people use the platform. You can accept analytics or continue with necessary cookies only. Learn more
