Menu

1 / 10

Better Gaussian Splatting in Julia

Hacker News·3 months ago
#ua7lSO32
#pxl-th#depth#dataset#geometry#gaussians
Reading 0:00
15s threshold

use WASD + Mouse or tap on the screen to walk around :)

Amulet of St. Michael in Kyiv, Ukraine

(reconstructed with GaussianSplatting.jl, ~6M Gaussians)

GaussianSplatting.jl 2.0 release brings notable quality of life improvements and new capabilities.

Same code, multiple GPU backends

Written entirely in Julia it supports following GPU backends:

AMD GPU (AMDGPU.jl)

NVIDIA GPU (CUDA.jl)

MacBook GPU(Metal.jl)

This is achieved with KernelAbstractions.jl that allows writing a single kernel that get's compiled to a specific target.

Multithreaded UI

To avoid freezing the app during heavy work (such as JIT compilation of GPU kernels, dataset loading, etc.) the app is now split into two threads:

Frontend: handles the UI, performs OpenGL rendering, dispatches commands to the backend.

Backend: performs Gaussian Splatting rendering, training, dataset loading, etc.

In this way, the UI always stays responsive and user can interact with it, even if there are long-standing jobs in the background.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.