AI Paper Atlas

Research map / 3D vision / 3D generation

AvatarStudio: High-Fidelity and Animatable 3D Avatar Creation from Text

Xuanmeng Zhang, Jianfeng Zhang, Chenxu Zhang, Jun Hao Liew, Huichao Zhang, Yi Yang, Jiashi Feng

IJCV 2025 · 3D vision › 3D generation · approach: Feed-forward 3D asset generation and editing · 14 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
use DensePose-conditioned ControlNet instead of Stable Diffusion guidance (ablation)AvatarStudio · pose controllabilitySMPL MSE (x10^-2): 9.0 -> 5.9Improved
use DensePose-conditioned ControlNet instead of skeleton ControlNet (ablation)AvatarStudio · pose controllabilitySMPL MSE (x10^-2): 7.7 -> 5.9Improved
add dual-space (canonical and deformed) training (ablation)AvatarStudio · pose controllabilitySMPL MSE (x10^-2): 6.5 -> 5.9Improved
combine NeRF and mesh instead of mesh-only (DMTet) (ablation)AvatarStudio · avatar qualityqualitativeImproved
combine NeRF and mesh instead of NeRF-only (ablation)AvatarStudio · avatar qualityqualitativeImproved
add CFG rescale (ablation)AvatarStudio · avatar appearancequalitativeImproved
add part-aware super-resolution (ablation)AvatarStudio · avatar appearancequalitativeImproved
use AvatarStudio instead of DreamWaltztext-to-3D avatar · specific charactersCLIP score: 31.52 -> 32.80Improved
use AvatarStudio instead of DreamHumantext-to-3D avatar · realistic humansCLIP score: 29.54 -> 32.17Improved
reduce training steps from 10,000 to 5,000 coarse and 3,000 to 2,000 fine (ablation)AvatarStudio · optimization timehours: 2.5 hours -> around 1 hourImproved

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