# ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction arXiv: https://arxiv.org/abs/2509.03775 ยท HTML: https://mlsanity.com/paper/2509.03775/ ## Key facts - Cited by 4 papers in the map (data through 14 Oct 2026). - Builds on 58 of its 70 references that are in the map. - First posted on arXiv 3 Sep 2025. ## Builds on (most cited first, 30 of 58) - [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023) - [Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields](https://mlsanity.com/paper/2111.12077/) (2021) - [4D Gaussian Splatting for Real-Time Dynamic Scene Rendering](https://mlsanity.com/paper/2310.08528/) (2023) - [DreamGaussian: Generative Gaussian Splatting for Efficient 3D Content Creation](https://mlsanity.com/paper/2309.16653/) (2023) - [Deformable 3D Gaussians for High-Fidelity Monocular Dynamic Scene Reconstruction](https://mlsanity.com/paper/2309.13101/) (2023) - [Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering](https://mlsanity.com/paper/2312.00109/) (2023) - [LightGaussian: Unbounded 3D Gaussian Compression with 15x Reduction and 200+ FPS](https://mlsanity.com/paper/2311.17245/) (2023) - [CAT3D: Create Anything in 3D with Multi-View Diffusion Models](https://mlsanity.com/paper/2405.10314/) (2024) - [Gaussian Grouping: Segment and Edit Anything in 3D Scenes](https://mlsanity.com/paper/2312.00732/) (2023) - [PhysGaussian: Physics-Integrated 3D Gaussians for Generative Dynamics](https://mlsanity.com/paper/2311.12198/) (2023) - [Compact 3D Gaussian Representation for Radiance Field](https://mlsanity.com/paper/2311.13681/) (2023) - [GS-LRM: Large Reconstruction Model for 3D Gaussian Splatting](https://mlsanity.com/paper/2404.19702/) (2024) - [GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting](https://mlsanity.com/paper/2311.14521/) (2023) - [GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting](https://mlsanity.com/paper/2311.11700/) (2023) - [Mini-Splatting: Representing Scenes with a Constrained Number of Gaussians](https://mlsanity.com/paper/2403.14166/) (2024) - [HAC: Hash-grid Assisted Context for 3D Gaussian Splatting Compression](https://mlsanity.com/paper/2403.14530/) (2024) - [EAGLES: Efficient Accelerated 3D Gaussians with Lightweight EncodingS](https://mlsanity.com/paper/2312.04564/) (2023) - [3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting](https://mlsanity.com/paper/2312.09228/) (2023) - [SplattingAvatar: Realistic Real-Time Human Avatars with Mesh-Embedded Gaussian Splatting](https://mlsanity.com/paper/2403.05087/) (2024) - [HUGS: Human Gaussian Splats](https://mlsanity.com/paper/2311.17910/) (2023) - [Reducing the Memory Footprint of 3D Gaussian Splatting](https://mlsanity.com/paper/2406.17074/) (2024) - [Gaussian in the Wild: 3D Gaussian Splatting for Unconstrained Image Collections](https://mlsanity.com/paper/2403.15704/) (2024) - [GaussCtrl: Multi-View Consistent Text-Driven 3D Gaussian Splatting Editing](https://mlsanity.com/paper/2403.08733/) (2024) - [RadSplat: Radiance Field-Informed Gaussian Splatting for Robust Real-Time Rendering with 900+ FPS](https://mlsanity.com/paper/2403.13806/) (2024) - [Human Gaussian Splatting: Real-time Rendering of Animatable Avatars](https://mlsanity.com/paper/2311.17113/) (2023) - [GaussianFlow: Splatting Gaussian Dynamics for 4D Content Creation](https://mlsanity.com/paper/2403.12365/) (2024) - [GaussianImage: 1000 FPS Image Representation and Compression by 2D Gaussian Splatting](https://mlsanity.com/paper/2403.08551/) (2024) - [PUP 3D-GS: Principled Uncertainty Pruning for 3D Gaussian Splatting](https://mlsanity.com/paper/2406.10219/) (2024) - [Speedy-Splat: Fast 3D Gaussian Splatting with Sparse Pixels and Sparse Primitives](https://mlsanity.com/paper/2412.00578/) (2024) - [DGE: Direct Gaussian 3D Editing by Consistent Multi-view Editing](https://mlsanity.com/paper/2404.18929/) (2024) ## Built on by (most cited first, 4 of 4) - [GS-Scale: Unlocking Large-Scale 3D Gaussian Splatting Training via Host Offloading](https://mlsanity.com/paper/2509.15645/) (2025) - [TideGS: Scalable Training of Over One Billion 3D Gaussian Splatting Primitives via Out-of-Core Optimization](https://mlsanity.com/paper/2605.20150/) (2026) - [Gaussian Splatting-based Volumetric Video Compression with Sparse 4D Anchors](https://mlsanity.com/paper/2609.33969/) (2026) - [SCION: Scene Composition with Instanced Neural Primitives](https://mlsanity.com/paper/2610.02322/) (2026) ## Abstract (arXiv) 3D Gaussian Splatting (3DGS) is a state-of-art technique to model real-world scenes with high quality and real-time rendering. Typically, a higher quality representation can be achieved by using a large number of 3D Gaussians. However, using large 3D Gaussian counts significantly increases the GPU device memory for storing model parameters. A large model thus requires powerful GPUs with high memory capacities for training and has slower training/rendering latencies due to the inefficiencies of memory access and data movement. In this work, we introduce ContraGS, a method to enable training directly on compressed 3DGS representations without reducing the Gaussian Counts, and thus with a little loss in model quality. ContraGS leverages codebooks to compactly store a set of Gaussian parameter vectors throughout the training process, thereby significantly reducing memory consumption. While codebooks have been demonstrated to be highly effective at compressing fully trained 3DGS models, directly training using codebook representations is an unsolved challenge. ContraGS solves the problem of learning non-differentiable parameters in codebook-compressed representations by posing parameter estimation as a Bayesian inference problem. To this end, ContraGS provides a framework that effectively uses MCMC sampling to sample over a posterior distribution of these compressed representations. With ContraGS, we demonstrate that ContraGS significantly reduces the peak memory during training (on average 3.49X) and accelerated training and rendering (1.36X and 1.88X on average, respectively), while retraining close to state-of-art quality.