HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
tg-bomze
Face-Depixelizer
Jupyter Notebook2020–2020
tg-bomze / Face-Depixelizer

Face-Depixelizer

Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.

Creative & Media
Explore on GitHubRead Hacker News discussions
2Distinct people
2Mentions
0Explicit recommenders
2.6KGitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

Face Depixelizer based on "PULSE: Self-Supervised Photo Upsampling via Latent Space Exploration of Generative Models" repository.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 7–Nov 14 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/14/2026, 5:04:57 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by day2 dated mentions

Observed mentions: 2020-06-20 16:47:45 UTC to 2020-07-01 02:22:24 UTC.

012020-06-20 00:00:00 UTC to 2020-06-21 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 commentsJun 202020-06-21 00:00:00 UTC to 2020-06-22 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-22 00:00:00 UTC to 2020-06-23 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-23 00:00:00 UTC to 2020-06-24 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-24 00:00:00 UTC to 2020-06-25 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-25 00:00:00 UTC to 2020-06-26 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsJun 252020-06-26 00:00:00 UTC to 2020-06-27 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-27 00:00:00 UTC to 2020-06-28 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-28 00:00:00 UTC to 2020-06-29 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-29 00:00:00 UTC to 2020-06-30 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-06-30 00:00:00 UTC to 2020-07-01 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2020-07-01 00:00:00 UTC to 2020-07-02 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsJul 1

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Jun 202020-06-20 00:00:00 UTC2020-06-21 00:00:00 UTC110
Jun 212020-06-21 00:00:00 UTC2020-06-22 00:00:00 UTC000
Jun 222020-06-22 00:00:00 UTC2020-06-23 00:00:00 UTC000
Jun 232020-06-23 00:00:00 UTC2020-06-24 00:00:00 UTC000
Jun 242020-06-24 00:00:00 UTC2020-06-25 00:00:00 UTC000
Jun 252020-06-25 00:00:00 UTC2020-06-26 00:00:00 UTC000
Jun 262020-06-26 00:00:00 UTC2020-06-27 00:00:00 UTC000
Jun 272020-06-27 00:00:00 UTC2020-06-28 00:00:00 UTC000
Jun 282020-06-28 00:00:00 UTC2020-06-29 00:00:00 UTC000
Jun 292020-06-29 00:00:00 UTC2020-06-30 00:00:00 UTC000
Jun 302020-06-30 00:00:00 UTC2020-07-01 00:00:00 UTC000
Jul 12020-07-01 00:00:00 UTC2020-07-02 00:00:00 UTC101

What Hacker News says

2 sources
grandmczeb·Jul 1, 2020
From the author's github[1] > We have noticed a lot of concern that PULSE will be used to identify individuals whose faces have been blurred out. We want to emphasize that this is impossible - PULSE makes imaginary faces of people who do not exist, which should not be confused for real people. It will not help identify or reconstruct the original image. This is just another way to generate realistic faces that match a pattern. The "bad use cases" I can imagine involve unmasking real people, which is not what the model does. [1] https://github.com/tg-bomze/Face-Depixelizer
In Yann LeCun quits Twitter amid acrimonious exchanges on AI bias

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.