Deep multi-frame face super-resolution

E. Ustinova; V. Lempitsky

RECORD

Deep multi-frame face super-resolution

E. Ustinova, V. Lempitsky

Computer Vision and Pattern Recognition · Submitted 10 Sep 2017

abstract compiled · 2026-09-23 · no language-model review

The authors' main claim We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution.

how it is stated · asserted 1.00 read the record →

Comment (0) Read on arXiv ↗

Cite ▾

Claim paper

The compiled record

The paper's own sentences, arranged. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. Numbers in the tables are the authors', checked by code. No sentence in this record was written by a model.

Open the compiled record

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-09-23: 1 request, 4,836 input tokens.

What the abstract itself states, as probabilities: claims first 0.05 · states limitation 0.14 · human participants 0.29 · controlled comparison 0.93 · randomized assignment 0.01 · states quantitative result 0.06 · compares with prior results 0.97 · mentions code or data availability 0.03.

The abstract, sentence by sentence

arXiv listing abstract v2. Results and the main claim are underlined; show every role.

Face verification and recognition problems have seen rapid progress in recent years, however recognition from small size images remains a challenging task that is inherently intertwined with the task of face super-resolution. Tackling this problem using multiple frames is an attractive idea, yet requires solving the alignment problem that is also challenging for low-resolution faces. Here we present a holistic system for multi-frame recognition, alignment, and superresolution of faces. Our neural network architecture restores the central frame of each input sequence additionally taking into account a number of adjacent frames and making use of sub-pixel movements. We present our results using the popular dataset for video face recognition (YouTube Faces). We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution.

background contribution method result interpretation main claim

What the classifier reports for each sentence. The number is the probability it gave the label.
#	sentence	role	the authors' own work	states the main conclusion	strength
s0	Face verification and recognition problems have seen rapid progress in recent years, however recognition from small size images remains a challenging task that is inherently intertwined with the task of face super-resolution.	background 0.98	0.05	0.04	asserted 1.00
s1	Tackling this problem using multiple frames is an attractive idea, yet requires solving the alignment problem that is also challenging for low-resolution faces.	background 0.84	0.06	0.03	asserted 0.82
s2	Here we present a holistic system for multi-frame recognition, alignment, and superresolution of faces.	contribution 1.00	0.90	0.14	asserted 0.98
s3	Our neural network architecture restores the central frame of each input sequence additionally taking into account a number of adjacent frames and making use of sub-pixel movements.	method 0.98	0.91	0.08	asserted 1.00
s4	We present our results using the popular dataset for video face recognition (YouTube Faces).	method 0.96	0.80	0.03	asserted 0.86
s5	We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution.	result 1.00	0.96	0.75	asserted 1.00

What kind of paper the classifier reports this is: method or tool 1.00 · evidence from observation or experiment 0.84.

What was examined, and what was not

sources read

arXiv listing abstract v2

not examined

full text
figures and tables
references and citing sentences
relations to other papers

levels run

P abstract

not run

S sections
T body sentences
C citations
R cross-paper relations

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. Every number in the measurements table is the authors', checked by code. Record as JSON

The paper

Original abstract

Face verification and recognition problems have seen rapid progress in recent years, however recognition from small size images remains a challenging task that is inherently intertwined with the task of face super-resolution. Tackling this problem using multiple frames is an attractive idea, yet requires solving the alignment problem that is also challenging for low-resolution faces. Here we present a holistic system for multi-frame recognition, alignment, and superresolution of faces. Our neural network architecture restores the central frame of each input sequence additionally taking into account a number of adjacent frames and making use of sub-pixel movements. We present our results using the popular dataset for video face recognition (YouTube Faces). We show a notable improvement of identification score compared to several baselines including the one based on single-image super-resolution.

Human review

How Pith checks papers → · Full audit of this paper →

How the literature uses it

1 arXiv paper cite this in 1 sentence

Each citing sentence is taken from the citing paper's LaTeX source and typed by Pith's classifier. A label appears at probability 0.8 or more (0.95 for support), a contest at 0.7 or more; the quoted words are the citing authors'. How each label was checked · JSON

Papers citing it

Cites it as background 1 paper

MFSR methods are also developed for specific applications, such as for handheld devices [ref] , to increase spatial resolution of face images [ref] , and in satellite imagery [ref] .

Burst Image Restoration and Enhancement · Related Work · 0.93

Discussion

Know something about this paper? Leave a comment, or highlight any passage above to comment on it.