$ show xiaobiaodu/Mobile-GS
This repository implements Mobile-GS, a real-time Gaussian splatting approach for novel view synthesis optimized for mobile devices. The system trains 3D Gaussian representations from multi-view images, applies compression techniques (vector quantization, Huffman coding, GPCC) to reduce model size, and renders novel views via differentiable EWA (Elliptical Weighted Average) splatting. It includes training pipelines (train.py, pretrain.py), rendering engine (gaussian_renderer/), scene management, custom CUDA kernels for efficient rasterization, and evaluation metrics. The architecture follows a modular design with separate components for training, rendering, scene handling, and compression, optimized for deployment on mobile platforms with limited computational resources.
The LLM identified 1 files worth highlighting for reuse:
Implements a comprehensive compression pipeline for 3D Gaussian models, combining vector quantization for feature/codebook compression, Huffman coding for entropy encoding, and GPCC integration (via tmc3) for geometry compression. Provides encode/decode methods in the Gaussian model that reduce storage requirements while maintaining visual quality. This self-contained module addresses the general problem of neural representation compression with a specialized solution that could be adapted for other 3D or neural network representations.