AI Paper Atlas

Research map / 3D vision / Gaussian splatting

ContraGS: Codebook-Condensed and Trainable Gaussian Splatting for Fast, Memory-Efficient Reconstruction

Sankeerth Durvasula, Sharanshangar Muhunthan, Zain Moustafa, Richard Chen, Ruofan Liang, Yushi Guan, Nilesh Ahuja, Nilesh Jain, Selvakumar Panneer, Nandita Vijaykumar

ICCV 2025 · 3D vision › Gaussian splatting · approach: Regularization and primitive design for 3DGS · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
train on codebook-compressed Gaussians instead of full parameters (2M Gaussians)3DGS-MCMC · MipNeRF360 (7 scenes, avg)Peak model memory (MB): 473.000 -> 130.038Improved
train on codebook-compressed Gaussians (2M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)PSNR: 30.71 -> 30.06Hurt
train on codebook-compressed Gaussians (2M)3DGS-MCMC · Deep Blending and Tanks and TemplesPSNR: 33.99 -> 33.73; 24.32 -> 24.35No clear effect
train on codebook-compressed Gaussians (5M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)PSNR: 32.72 -> 31.01Hurt
train on codebook-compressed Gaussians (5M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)Peak model memory (MB): 1182.000 -> 275.594Improved
train on codebook-compressed Gaussians (2M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)Training speed (it/s): 23.65 -> 32.02Improved
train on codebook-compressed Gaussians (2M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)FPS: 102 -> 216Improved
train on codebook-compressed Gaussians (5M)3DGS-MCMC · MipNeRF360 (7 scenes, avg)FPS: 65 -> 87Improved
raise Gaussian cap from 2M to 5M (ablation)ContraGS · MipNeRF360 (7 scenes, avg)PSNR: 30.06 -> 31.01Improved
use ContraGS-5M instead of MCMC-2M3DGS-MCMC · MipNeRF360 (7 scenes, avg)PSNR: 30.71 -> 31.01Improved
use ContraGS-2M instead of 3DGS3DGS · MipNeRF360 (7 scenes, avg)Peak model memory (MB): 2089.363 -> 130.038Improved
use ContraGS-2M instead of 3DGS (random init Blender)3DGS · Blender (8 scenes, random init)PSNR: 31.07 -> 36.840Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy