Paper page - MFVSR: A Multi-Style and Fine-Grained Benchmark for Video Subtitle Removal

Source: https://huggingface.co/papers/2610.18461

Abstract

MFVSR introduces a large-scale, multi-style benchmark for video subtitle removal that evaluates restoration fidelity, preservation, temporal consistency, and reliability through fine-grained, spatially decoupled protocols.

Video subtitle removal(VSR) is an important video restoration task, yet existing evaluation remains limited by low-resolution datasets, fragmented test sets, and generic video-inpainting protocols that fail to adequately capture localized restoration errors, unintended modifications, temporal instability, and incomplete outputs. In this paper, we introduceMFVSR, a large-scalemulti-style benchmarkfor fine-grained and reliability-awarevideo subtitle removalevaluation.MFVSRdistinguishes itself through three key features: (1) Large-scale and diverse data, comprising 3,000 paired videos from Real-HQ, Real-LQ, and AI-Generated sources, with an auxiliary set of 953 in-the-wild real videos for real-world coverage analysis; (2) Controlled subtitle diversity, spanning 16 languages and four factors covering spatial layout, temporal behavior, visual style, and language mode; (3) Fine-grained evaluation, introducing an information-conditioned, spatially decoupled protocol that separates blind frommask-guided removaland measuresRestoration Fidelity,Preservation Fidelity,Temporal Fidelity, coverage, and failures. Experiments on six representative methods reveal substantial discrepancies between local restoration, outside-region preservation, temporal consistency, and full-set reliability that are obscured by conventional full-frame metrics.MFVSRtherefore provides a more comprehensive and diagnostic foundation for evaluating and advancingvideo subtitle removalmethods.

View arXiv pageView PDFGitHub3Add to collection

Get this paper in your agent:

hf papers read 2610\.18461

Don’t have the latest CLI?curl \-LsSf https://hf\.co/cli/install\.sh \| bash

Models citing this paper0

No model linking this paper

Cite arxiv.org/abs/2610.18461 in a model README.md to link it from this page.

Datasets citing this paper1

#### siiian/MFVSR Viewer• Updated2 days ago • 3k • 183

Spaces citing this paper0

No Space linking this paper

Cite arxiv.org/abs/2610.18461 in a Space README.md to link it from this page.

Collections including this paper0

No Collection including this paper

Add this paper to acollectionto link it from this page.