Distilled-3DGS:Distilled 3D Gaussian Splatting
This work addresses a memory bottleneck in 3D reconstruction for applications like VR/AR, though it is incremental as it builds on existing 3DGS techniques.
The paper tackles the high memory and storage requirements of 3D Gaussian Splatting for novel view synthesis by proposing a knowledge distillation framework that uses aggregated teacher models and a structural similarity loss to train a lightweight student model, achieving improved rendering quality and storage efficiency compared to state-of-the-art methods.
3D Gaussian Splatting (3DGS) has exhibited remarkable efficacy in novel view synthesis (NVS). However, it suffers from a significant drawback: achieving high-fidelity rendering typically necessitates a large number of 3D Gaussians, resulting in substantial memory consumption and storage requirements. To address this challenge, we propose the first knowledge distillation framework for 3DGS, featuring various teacher models, including vanilla 3DGS, noise-augmented variants, and dropout-regularized versions. The outputs of these teachers are aggregated to guide the optimization of a lightweight student model. To distill the hidden geometric structure, we propose a structural similarity loss to boost the consistency of spatial geometric distributions between the student and teacher model. Through comprehensive quantitative and qualitative evaluations across diverse datasets, the proposed Distilled-3DGS, a simple yet effective framework without bells and whistles, achieves promising rendering results in both rendering quality and storage efficiency compared to state-of-the-art methods. Project page: https://distilled3dgs.github.io . Code: https://github.com/lt-xiang/Distilled-3DGS .