AI Paper Atlas

Research map / 3D vision / Gaussian splatting

MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition

Aggelina Chatziagapi, Grigorios Chrysos, Dimitris Samaras

ECCV 2024 · 3D vision › Gaussian splatting · approach: Animatable Gaussian human avatars · 2 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
learn a single multi-identity CP-decomposed 3DGS representation instead of per-identity 3DGS-AvatarMIGS · AIST++ Advanced TestPSNR: 25.51 -> 26.54Improved
learn multi-identity representation from 30 identities on AIST++ Basic TestMIGS · AIST++ Basic TestPSNR: 28.89 -> 29.82Improved
multi-identity training versus single-identity 3DGS-Avatar on novel view synthesisMIGS · ZJU-MoCap subject 387LPIPS*: 34.24 -> 35.33Mixed
use CP rank R=100 instead of R=10 (ablation)MIGS · AIST++ Advanced TestLPIPS*Improved
increase rank from R=100 to R=200 with personalization (ablation)MIGS · AIST++ Advanced TestLPIPS*No clear effect
increase number of training identities (ablation)MIGS · AIST++ Advanced TestLPIPS*Improved
add personalization by fine-tuning color MLP only (ablation)MIGS · AIST++ Advanced Testvisual qualityImproved
fine-tune all parameters instead of only color MLP during personalization (ablation)MIGS · AIST++ novel posesartifacts (qualitative)Hurt
update only the identity's row of U2 versus the full U2 each iteration (ablation)MIGS · trainingvisual qualityNo clear effect
remove adaptive densification and pruning of Gaussians (ablation)MIGS single identity · single identityvisual qualityNo clear effect

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 3 of 3 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