AI Paper Atlas

Research map / 3D vision / 3D generation

LiP-Flow: Learning Inference-Time Priors for Codec Avatars via Normalizing Flows in Latent Space

Emre Aksan, Shugao Ma, Akin Caliskan, Stanislav Pidhorskyi, Alexander Richard, Shih-En Wei, Jason Saragih, Otmar Hilliges

ECCV 2022 · 3D vision › 3D generation · approach: Diffusion-based novel view synthesis · 1 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 latent likelihood term L_L to fitting objective (ablation)LiP-Flow · HMC fitting (one subject)PSNR: 30.34 -> 33.61Improved
add prior initialization of latent code (ablation)LiP-Flow · HMC fitting (one subject)geometry error: 0.405 -> 0.060Improved
add prior initialization and L_L together (ablation)LiP-Flow · HMC fitting (one subject)PSNR: 28.51 -> 33.61Improved
add flow cycle in training (ablation)LiP-Flow · HMC fitting (one subject)PSNR: 33.07 -> 33.61Improved
decode samples from P space as well as Q (ablation)LiP-Flow · HMC fitting (one subject)PSNR: 33.61 -> 33.03Hurt
replace KL-divergence with normalizing flow between prior and encoder spacesLiP-KL-HMC · HMC fittingPSNR: 34.36 -> 34.98Improved
replace KL-divergence with normalizing flowLiP-KL-KPT · Keypoint fittinggeometry error: 0.089 -> 0.053Improved
replace standard Gaussian prior with learned conditional priorDAM · HMC fittingPSNR: 31.65 -> 34.98Improved
train inference encoder as prior with flow instead of separate regressorDAM-HMC Reg. · HMC fittinggeometry error: 0.248 -> 0.087Improved
replace KL with flow (KPT prior) on DAM-encoder reconstructionLiP-KL-KPT · ReconstructionPSNR: 35.71 -> 36.22Improved
train LiP-KL prior jointly with DAMDAM · ReconstructionPSNR: 36.05 -> 35.79Hurt
add unconditional latent flow to DAM (ablation)DAM · Frontal fitting (one subject)PSNR: 34.67 -> 35.49Improved

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