AI Paper Atlas

Research map / Video / Video generation

World Reconstruction From Inconsistent Views

Lukas Höllein, Matthias Niessner

ECCV 2026 · Video › Video generation · approach: World-model video generation · 8 citations (OpenAlex)

Read the paper

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 non-rigid alignment and non-rigid aware Gaussian Splatting instead of DA3 reconstructionDA3 · Single video 3D reconstruction (avg over source video models)3D consistency: 69.53 -> 79.29Improved
use non-rigid alignment and non-rigid aware Gaussian Splatting instead of DA3 reconstructionDA3 · Single video 3D reconstruction (avg over source video models)photometric consistency: 71.62 -> 86.59Improved
use non-rigid alignment instead of VGGT-XVGGT-X · Single video 3D reconstruction (avg over source video models)CLIP-IQA+: 38.21 -> 46.56Improved
use non-rigid alignment instead of VGGT-X dagger variantVGGT-X dagger · Single video 3D reconstruction (avg over source video models)3D consistency: 69.66 -> 79.29Improved
use non-rigid alignment instead of 3DGS-MCMC3DGS-MCMC · Single video 3D reconstruction (avg over source video models)photometric consistency: 69.58 -> 86.59Improved
use non-rigid alignment instead of VGGT-X dagger variantVGGT-X dagger · Single video 3D reconstruction (avg over source video models)CLIP Aesthetic: 37.53 -> 37.61No clear effect

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