AI Paper Atlas

Research map / 3D vision / NeRF and radiance fields

FaceCLIPNeRF: Text-driven 3D Face Manipulation using Deformable Neural Radiance Fields

Sungwon Hwang, Junha Hyung, Daejin Kim, Min-Jung Kim, Jaegul Choo

ICCV 2023 · 3D vision › NeRF and radiance fields · approach: Sparse-input NeRF regularization · 15 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
replace single-latent-code inversion with Position-conditional Anchor Compositor (PAC)HyperNeRF + I · Text-driven face manipulationR-Precision: 0.342 -> 0.780Improved
PAC with HyperNeRF scene manipulator instead of CLIP fine-tuning of whole NeRFNeRF + FT · Text-driven face manipulationLPIPS: 0.350 -> 0.082Improved
add Lipschitz regularization L_lip to scene manipulator (ablation)FaceCLIPNeRF · crying face manipulationvisual quality (qualitative)Improved
add total variation loss L_ACR on anchor composition ratio (ablation)FaceCLIPNeRF · crying face manipulationnaturalness of face parts (qualitative)Improved
PAC instead of vanilla inversionHyperNeRF + I · User studytext reflectivity: 2.52 -> 4.15Improved

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