AI Paper Atlas

Research map / Video / Video generation

T2Bs: Text-to-Character Blendshapes via Video Generation

Jiahao Luo, Chaoyang Wang, Michael Vasilkovsky, Vladislav Shakhrai, Di Liu, Peiye Zhuang, Sergey Tulyakov, Peter Wonka, Hsin-Ying Lee, James Davis, Jian Wang

ICCV 2025 · Video › Video generation · approach: Trajectory-guided motion control · 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 view-conditioned deformation to VCDGS (ablation)VCDGS · Objaverse-XL geometrypoint-to-point error: 0.0632 -> 0.0576Improved
add color offset prediction (RefineMLP) (ablation)VCDGS · Objaverse-XL geometrynormal consistency error: 0.1851 -> 0.1611Improved
add linear blend skinning with control points instead of per-Gaussian deformation (ablation)VCDGS · Objaverse-XL geometrynormal consistency error: 0.2654 -> 0.1611Improved
add RefineMLP under simulated temporal appearance inconsistency (ablation)VCDGS · Objaverse-XL noisy texturesnormal consistency error: 0.2430 -> 0.1671Improved
fit VCDGS on SV4D multi-view videos instead of 4Real-Video (ablation)VCDGS · Objaverse-XL image qualityFID: 59.6 -> 56.6No clear effect
apply VCDGS to refine raw 4Real-Video output (ablation)4Real-Video · Objaverse-XL image qualityFID: 151.7 -> 59.6Improved
use 2000 control points instead of 200, 500 or 1000 (ablation)VCDGS · qualitative facial motionfine-grained motion captureImproved
use skeletons from UniRig or MagicArticulate instead of KNN control points (ablation)VCDGS · facial expressionssuitabilityHurt

Earlier methods this paper compares with

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