A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
-
Updated
Feb 26, 2025 - Python
A geometry-shader-based, global CUDA sorted high-performance 3D Gaussian Splatting rasterizer. Can achieve a 5-10x speedup in rendering compared to the vanialla diff-gaussian-rasterization.
A lightweight point-based visualization tool used for inspecting Gaussian data, designing camera motion, and exporting setups for external Gaussian renderers.
Visionary: The World Model Carrier Built on WebGPU-Powered Gaussian Splatting Platform
Official PyTorch implementation of QUEEN: QUantized Efficient ENcoding of Dynamic Gaussians for Streaming Free-viewpoint Videos (NeurIPS 2024)
Official code of "Fully Explicit Dynamic Gaussian Splatting (NeurIPS 2024)"
Code for 4D Gaussian Splatting: a scalable, memory-efficient method for dynamic scenes enabling real-time rendering of long sequences on consumer GPUs. Features multi-optimizer training, differential batching, and per-frame PLY storage while keeping high visual fidelity . Python, PyTorch, CUDA.
Archive for Scene Representation and Reconstruction for Novel-view Synthesis
Add a description, image, and links to the 4dgs topic page so that developers can more easily learn about it.
To associate your repository with the 4dgs topic, visit your repo's landing page and select "manage topics."