AI Paper Atlas

Research map / 3D vision / Face and shape

HumanNOVA: Photorealistic, Universal and Rapid 3D Human Avatar Modeling from a Single Image

Hezhen Hu, Wangbo Zhao, Lanqing Guo, Hanwen Jiang, Jonathan C. Liu, Zhiwen Fan, Kai Wang, Zhangyang Wang, Georgios Pavlakos

CVPR 2026 · 3D vision › Face and shape · approach: Gaussian and implicit head avatars · 0 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 generated data to Real3D fine-tuningReal3D · CustomHuman (frontal input)PSNR: 17.13 -> 20.97Improved
add generated data to Real3D fine-tuningReal3D · CustomHuman (frontal input)LPIPS: 95.12 -> 58.54Improved
add SMPL-X vertex initialization instead of COLMAPreal-world data generation (3DGS fitting) · multi-camera human capturePSNR: 16.49 -> 36.38Improved
add SMPL-X vertex initialization instead of COLMAPreal-world data generation (3DGS fitting) · multi-camera human captureoptimization time: 40 minutes to 4 minutesImproved
add the SMPL mesh prior (ablation)HumanNOVA · CustomHuman (frontal input)LPIPS: 2.3% relative improvementImproved
use triplane size larger than 32 (ablation)HumanNOVA · CustomHuman (frontal input)rendering qualityImproved
increase portion of generated training data (ablation)HumanNOVA · CustomHuman (frontal input)rendering qualityImproved
use Sapiens instead of DINOv2 as visual encoder (ablation)HumanNOVA · CustomHuman (frontal input)LPIPS: 42.42 -> 46.52No clear effect
use 4 fusion layers instead of 2 (ablation)HumanNOVA · CustomHuman (frontal input)LPIPS: 50.65 -> 42.42Improved
use 4 supervision views instead of 2 (ablation)HumanNOVA · CustomHuman (frontal input)LPIPS: 45.18 -> 42.42Improved
train with CustomHuman held out (leave-one-out) (ablation)HumanNOVA · CustomHuman (frontal input)LPIPS: 42.42 -> 44.22No clear effect
use the human-specific HumanNOVA instead of SiTHsingle-image avatar reconstruction · CustomHuman (frontal input)LPIPS: 41.8% relative LPIPS gainImproved

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