Distilled-3DGS:Distilled 3D Gaussian Splatting
Lintao Xiang, Xinkai Chen, Jianhuang Lai, Guangcong Wang

TL;DR
This paper introduces Distilled-3DGS, a knowledge distillation framework for 3D Gaussian Splatting that reduces memory usage while maintaining high-quality novel view synthesis.
Contribution
It is the first to apply knowledge distillation to 3D Gaussian Splatting, improving efficiency and rendering quality with a lightweight student model guided by multiple teacher models.
Findings
Achieves comparable rendering quality with significantly fewer 3D Gaussians.
Reduces memory and storage requirements for 3D Gaussian Splatting.
Demonstrates effectiveness across diverse datasets.
Abstract
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…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
