Skip to content
Preprint

AlbumVSR: Identity-Preserving Face Video Super-Resolution from a Personal Photo Album

Oct 2026 · 0 citations · 29 references
Computer Science Engineering

TL;DR

AlbumVSR conditions a frozen, one-step streaming diffusion transformer on a personal album, which uses photographs of the same person as an external source of identity.

Abstract

Severe blur, downsampling, noise, and compression can erase the identity cues needed to faithfully restore a person's face. We therefore use photographs of the same person as an external source of identity. AlbumVSR conditions a frozen, one-step streaming diffusion transformer on a personal album. We use four MagFace/CLIP set tokens to encode the album, and 64 texture tokens which come from a fused UV atlas rendered at the current window's estimated face pose. These tokens are appended to the transformer's cached cross-attention context. On an identity-disjoint VoxCeleb2 benchmark with heavy synthetic degradation, AlbumVSR raises ArcFace similarity to the ground truth from 0.586 to 0.670 and face PSNR from 24.98 to 26.71 dB. On the 91 test identities, its mean identity similarity is higher than that of all 14 baselines.

View source

Similar papers

Open access 2026

Auditing the Face Condition Port in Diffusion-Based Video Character Animation: Identity Suppression and an Identity–Expression Trade-Off

A reference-conditioned animator ships with a graph feeding its face condition port a perframe crop of the driver’s face that suppresses the target identity rather than transferring the driver’s, and a portrait animator outperforms everything measured here.

Kihong Kim, Peng-Hui Li · 0 citations
Preprint Oct 2026

Expression-Diverse References for Identity-Preserving Video Generation

Identity-preserving video generation aims to maintain a subject's identity while synthesizing realistic videos. Yet a single reference portrait captures the subject's appearance under only one facial configuration. As expressions change, facial appearance can vary in highly identity-specific ways, leaving the subject's...

Tian-Wen Fu, Wen-Bin Teng, Gong-Lin Chen et al. · 0 citations
Sep 2026

FANVIDv2: Evaluating Video Super-Resolution by Face and Licence-Plate Recognition Under Compound Degradation

Video super-resolution (VSR) is normally judged by PSNR and SSIM on clips that were downsampled bicubically, although in surveillance its purpose is to make faces and licence plates \emph{recognisable}. We present FANVIDv2, a benchmark that scores VSR by what a recognition pipeline can do with its output. FANVIDv2 prov...

Kavitha Viswanathan, Vrinda Goel, Shlesh Gholap et al. · 0 citations
#machine learning Preprint Oct 2026

Does an Illumination Prior Help Face-Swap Detection? A Controlled Study of Temporal Self-Blended Images

Self-blended images are widely used to train face-swap detectors, but primarily capture blending artifacts. We investigate whether adding illumination inconsistencies improves detection. Temporal Self-Blended Images (T-SBI) transfer lighting statistics between frames of the same video, with the mismatch controlled by l...

D. Davydov, Bader Rasheed, D. Vatolin · 0 citations
Preprint Oct 2026

CVBL-CCTV-Face Dataset for Real-World Face Enhancement and Recognition in Surveillance

In real-world surveillance settings, facial captures from closed-circuit television systems suffer from degradations such as low resolution, motion blur, noise, and occlusions, which undermine dependable face recognition. In this study, we propose a framework for super-resolution and identity recognition, aimed at surv...

Manish Das, Ajay Kumar Yadav, S. Dubey et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.