AI Paper Atlas

Research map / Video / Video generation

Gloria: Consistent Character Video Generation via Content Anchors

Yuhang Yang, Fan Zhang, Huaijin Pi, Ailing Zeng, Shuai Guo, Guowei Xu, Wei Zhai, Yang Cao, Zheng-Jun Zha

CVPR 2026 · Video › Video generation · approach: Compositional text-to-video diffusion · 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
add global anchor (ablation)Gloria · Long-term consistencyArcFace identity: 0.233 -> 0.787Improved
add global anchor (ablation)Gloria · Long-term consistencysubject consistency: 0.840 -> 0.960Improved
add Superset Content Anchoring (ablation)Gloria · Long-term consistencyArcFace identity: 0.489 -> 0.787Improved
add Superset Content Anchoring (ablation)Gloria · Long-term consistencybackground consistency: 0.899 -> 0.951Improved
add viewpoint and expression anchors (ablation)Gloria · Multi-view appearance and expressive IDExpression ArcFace: 0.668 -> 0.717Improved
add viewpoint and expression anchors (ablation)Gloria · Multi-view appearance and expressive IDDINO-I: 0.801 -> 0.821Improved
add RoPE as Weak Condition (ablation)Gloria · Multi-view appearance and expressive IDExpression ArcFace: 0.671 -> 0.717Improved
add RoPE as Weak Condition (ablation)Gloria · Multi-view appearance and expressive IDDINO-I: 0.817 -> 0.821Improved
scale model from 5B to 17B (ablation)Gloria · Model size (10M clips)ArcFace: 0.583 -> 0.787Improved
scale training data from 2M to 10M clips (ablation)Gloria 17B · Data scaleArcFace: 0.623 -> 0.787Improved
scale training data from 2M to 10M clips (ablation)Gloria 17B · Data scaleAES: 3.57 -> 3.63Improved
add Gemini judge to EmotiEffLib for expression anchors (ablation)data pipeline · Expression anchor extraction (100 samples)accuracy: 66% -> 82%Improved

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