AI Paper Atlas

Research map / Video / Video generation

VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs

Anna Frühstück, Nikolaos Sarafianos, Yuanlu Xu, Peter Wonka, Tony Tung

CVPR 2023 · Video › Video generation · approach: Diffusion-based human image animation · 18 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
jointly invert multiple frames and fine-tune a personalized 3D-aware generator (ablation)VIVE3D · Ablation videosFace Similarity: 0.7382 -> 0.9101Improved
fine-tune the personalized generator (ablation)VIVE3D · Ablation videosFace Similarity: 0.7191 -> 0.9101Improved
use flow-based view correction when compositing (ablation)VIVE3D · Ablation videosPSNR: 24.8845 -> 35.5367Improved
regularize per-frame offsets around a shared identity latent (ablation)VIVE3D · Ablation videosFace Similarity: 0.8007 -> 0.9101Improved
use VIVE3D instead of StiiT for age editingvideo face editing · VoxCeleb, age editingSimilarity to Source: 0.7891 -> 0.8381Improved
use VIVE3D instead of StiiT for angle editingvideo face editing · VoxCeleb, angle editingSimilarity to Source: 0.6695 -> 0.8694Improved
use VIVE3D rather than StiiT for inversionvideo face inversion · VoxCeleb, inversionSSIM: 0.9798 -> 0.9704Hurt

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