AI Paper Atlas

Research map / Image generation / Editing and style transfer

FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models

Hao ZHANG, Tianyuan DAI, Yanbo Xu, Yu-Wing Tai, Chi-Keung Tang

NeurIPS 2023 · Image generation › Editing and style transfer · approach: Diffusion face generation and editing · 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 diffusion SDS guidance instead of CLIP guidance for text editingFaceDNeRF · Text-edit examples vs StyleCLIP Latent OptimizationClip loss / visual quality: 7.49 vs 6.53Mixed
Compare identity preservation against StyleCLIP Latent OptimizationFaceDNeRF · Text-edit examplesID loss x100: 2.40 -> 2.26Improved
Edit in GAN latent space instead of InterfaceGAN linear direction (Young)FaceDNeRF · Young editID loss: 0.0159 -> 0.0102Improved
Edit in GAN latent space instead of InterfaceGAN linear direction (Smile)FaceDNeRF · Smile editID loss: 0.0105 -> 0.0028Improved
Edit in GAN latent space instead of InterfaceGAN linear direction (Mustache)FaceDNeRF · Mustache editID loss: 0.0148 -> 0.0014Improved
Increase identity loss weight lambda_ID (ablation)FaceDNeRF · Prompt 'A bald man with a thick mustache'similarity to input identity (qualitative)Improved
Increase reconstruction loss weight lambda_R (ablation)FaceDNeRF · Prompt 'A bald man with a thick mustache'text-edit fidelity (qualitative)Mixed
Increase diffusion loss weight lambda_D (ablation)FaceDNeRF · Prompt 'A bald man with a thick mustache'text guidance strength (qualitative)Improved
Use SDS in GAN latent space rather than original SDS on unconstrained NeRF (ablation)FaceDNeRF · Text-conditioned head generationgeneration quality (qualitative)Improved
Use SDS guidance instead of CLIP guidance (ablation)FaceDNeRF · Face editing with attribute promptsimage quality (qualitative)Improved
Use short difference-only prompt instead of full description (ablation)FaceDNeRF · Editing promptsedit success (qualitative)No clear effect
Use ambiguous single-word prompt 'Old' or 'senior' instead of 'An old man' (ablation)FaceDNeRF · Editing promptsedit success (qualitative)Hurt

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