AI Paper Atlas

Research map / 3D vision / Gaussian splatting

VoluMe - Authentic 3D Video Calls from Live Gaussian Splat Prediction

Martin de La Gorce, Charlie Hewitt, Tibor Takács, Robert Gerdisch, Zafiirah Hosenie, Givi Meishvili, Marek Kowalski, Thomas J. Cashman, Antonio Criminisi

ICCV 2025 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 4 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
add jitter stability loss L_j (ablation)VoluMe · Ava256 250 subjectsJitter: 0.005020 -> 0.004967Improved
add jitter stability loss L_j (ablation)VoluMe · Ava256 250 subjectsLPIPS: 0.1581 -> 0.1497Improved
predict two Gaussians per pixel instead of one (ablation)VoluMe · Ava-256 ablationPSNR: 18.907 -> 19.069Improved
add ROI homography instead of simple cropping (ablation)VoluMe · Ava-256 ablationPSNR: 18.901 -> 19.069Improved
add direct colour sampling (ablation)VoluMe · Ava-256 ablationPSNR: 19.026 -> 19.069Improved
add optimizable layers (ablation)VoluMe · Ava-256 ablationPSNR: 19.005 -> 19.069Improved
combine all five features vs baseline (ablation)VoluMe · Ava-256 ablationPSNR: 18.698 -> 19.069Improved
combine all five features vs baseline (ablation)VoluMe · Ava-256 ablationJitter: 0.004959 -> 0.004967No clear effect
use two Gaussians per pixel instead of one (ablation)VoluMe · Ava-256 (60 epochs)PSNR: 19.07 -> 19.15Improved
use three Gaussians per pixel instead of two (ablation)VoluMe · Ava-256 (60 epochs)PSNR: 19.15 -> 18.99Hurt
use four Gaussians per pixel instead of two (ablation)VoluMe · Ava-256 (60 epochs)Jitter: 0.005086 -> 0.005990Hurt
use VoluMe instead of Splatter ImageVoluMe · Cafca subsetLPIPS: 0.2244 -> 0.1868Improved

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