Pith. sign in

REVIEW 1 cited by

DicFace: Dirichlet-Constrained Variational Codebook Learning for Temporally Coherent Video Face Restoration

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2506.13355 v1 pith:3LDZYCJJ submitted 2025-06-16 cs.CV

classification cs.CV
keywords restorationvideofacefacialvariationalwhilechallengecodebook
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Video face restoration faces a critical challenge in maintaining temporal consistency while recovering fine facial details from degraded inputs. This paper presents a novel approach that extends Vector-Quantized Variational Autoencoders (VQ-VAEs), pretrained on static high-quality portraits, into a video restoration framework through variational latent space modeling. Our key innovation lies in reformulating discrete codebook representations as Dirichlet-distributed continuous variables, enabling probabilistic transitions between facial features across frames. A spatio-temporal Transformer architecture jointly models inter-frame dependencies and predicts latent distributions, while a Laplacian-constrained reconstruction loss combined with perceptual (LPIPS) regularization enhances both pixel accuracy and visual quality. Comprehensive evaluations on blind face restoration, video inpainting, and facial colorization tasks demonstrate state-of-the-art performance. This work establishes an effective paradigm for adapting intensive image priors, pretrained on high-quality images, to video restoration while addressing the critical challenge of flicker artifacts. The source code has been open-sourced and is available at https://github.com/fudan-generative-vision/DicFace.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Persistent Free Volume Governs (Anti)plasticization in Chitosan-Water Mixtures

    cond-mat.soft 2026-04 unverdicted novelty 5.0 of 10

    Dynamically accessible free volume, enabled by connected water-accessible regions, is proposed to govern antiplasticization then plasticization of elastic properties in chitosan–water mixtures.

Pith tools