AI Paper Atlas

Research map / 3D vision / 3D generation

TeRA: Rethinking Text-guided Realistic 3D Avatar Generation

Yanwen Wang, Yiyu Zhuang, Jiawei Zhang, Li Wang, Yifei Zeng, Xun Cao, Xinxin Zuo, Hao Zhu

ICCV 2025 · 3D vision › 3D generation · approach: Text-to-3D scene generation · 3 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 TeRA feedforward latent diffusion instead of SDS optimization (HumanNorm)HumanNorm · Text-to-3D avatar generationgeneration time: 4.0h -> 12sImproved
use TeRA instead of HumanNorm: user-study realismHumanNorm · Text-to-3D avatar generationuser study realism: 3.04 -> 4.35Improved
use TeRA instead of HumanNorm: user-study text consistencyHumanNorm · Text-to-3D avatar generationuser study text consistency: 3.79 -> 4.54Improved
use TeRA instead of HumanNorm: user-study visual qualityHumanNorm · Text-to-3D avatar generationuser study visual quality: 3.01 -> 4.33Improved
use TeRA instead of X-Oscar: CLIP scoreX-Oscar · Text-to-3D avatar generationCLIP Score: 32.46 -> 30.17Hurt
use TeRA instead of HumanNorm: VQA scoreHumanNorm · Text-to-3D avatar generationVQA Score: 0.72 -> 0.82Improved
use TeRA instead of HumanGaussian: VQA scoreHumanGaussian · Text-to-3D avatar generationVQA Score: 0.82 -> 0.82No clear effect
raise structured latent resolution from 128x128 to 256x256 (ablation)TeRA · TeRA latent space ablationqualitative artifacts (Fig.)Improved
use diffusion inpainting on structured latent instead of direct feature swapping for virtual try-on (ablation)TeRA · virtual try-on editingqualitative artifacts (Fig.)Improved
add distillation module linking diffusion model to VAE encoder (instead of direct connection) (ablation)TeRA · TeRA traininggeneration qualityImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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