AI Paper Atlas

Research map / 3D vision / Gaussian splatting

DynMF: Neural Motion Factorization for Real-time Dynamic View Synthesis with 3D Gaussian Splatting

Angelos Kratimenos, Jiahui Lei, Kostas Daniilidis

ECCV 2024 · 3D vision › Gaussian splatting · approach: Monocular dynamic scene reconstruction · 100 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
use a learned MLP time-basis instead of a Fourier basis (ablation)DynMF · D-NeRF MutantPSNR (dB): 33.17 -> 40.79Improved
use a learned basis instead of Fourier 10 (ablation)DynMF · N3DV Flame-steakPSNR (dB): 28.95 -> 31.57Improved
increase number of trajectories from 1 to 10 (ablation)DynMF · D-NeRF MutantPSNR (dB): 29.75 -> 40.79Improved
increase number of trajectories beyond 10 (20 or 50) (ablation)DynMF · D-NeRF MutantPSNR (dB): 40.79 -> 40.53No clear effect
increase time positional-encoding frequencies from 1 to 32 (ablation)DynMF · N3DV Flame-steakPSNR (dB): 29.32 -> 31.57Improved
increase time encoding from 32 to 60 frequencies (ablation)DynMF · N3DV Flame-steakPSNR (dB): 31.57 -> 29.80Hurt
add a rigidity loss on motion coefficients (ablation)DynMF · dynamic scenesrender qualityNo clear effect
use DynMF instead of 4DGS and Gaufredynamic 3D Gaussian splatting · D-NeRFPSNR (dB): 34.80 -> 36.89Improved
use DynMF instead of 4DGSdynamic 3D Gaussian splatting · N3DVPSNR (dB): 32.01 -> 31.70No clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 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