Share this page!

Dmytro Mishkin Profile picture
Twitter logo
21 Dec, 3 tweets, 3 min read
Scale-Net: Learning to Reduce Scale Differences for Large-Scale Invariant Image Matching

tl;dr: same idea as with other ScaleNet: estimate scale difference in 2 images-> resize them. Eval on their version of Scale IMC
1/2 (check 2nd)
Yujie Fu, Yihong Wu
arxiv.org/abs/2112.10485
In order to prove priority and originality of the idea w.r.t. @axelbarrosotw ScaleNet, authors included #ICCV2021 submission screenshot as a proof.
Weird, however that current paper has less authors.
2/2
This is other ScaleNet

• • •

Missing some Tweet in this thread? You can try to force a refresh
　

Keep Current with Dmytro Mishkin

Dmytro Mishkin Profile picture

Stay in touch and get notified when new unrolls are available from this author!

Read all threads

This Thread may be Removed Anytime!

PDF

Twitter may remove this content at anytime! Save it as PDF for later use!

Try unrolling a thread yourself!

how to unroll video
  1. Follow @ThreadReaderApp to mention us!

  2. From a Twitter thread mention us with a keyword "unroll"
@threadreaderapp unroll

Practice here first or read more on our help page!

More from @ducha_aiki

Dmytro Mishkin Profile picture
30 Nov
After 16 hours working on a video for presentation, it crossed my mind that it would be a great idea before going to bed, to upgrade my desktop from Ubuntu 16.04 to 20.04 (yes, at 2:30 am).
What could possibly go wrong?
To summarize:
1st problem were some binaries from zoom installed.
Then it clashed with libgl -mesa-something. Nvidia drivers got involved

What helped, is running apt -o Dpkg::Options::="--force-overwrite"
2/
2)After half-successfully updates to 18.04, internet connection disappeared
askubuntu.com/a/1021885/2413…

3)Oh, and everything with very weird "zoomed-in" thing and no windows manager working.
After update to 20.04 and cuda/nvidia driver installation, windows were up. But huuuge
3/
Read 4 tweets
Dmytro Mishkin Profile picture
14 Nov
This is a nice counter example against my arguments for arXiv.

The situation is following, in thread:
1) relatively small group gets the ideas of AE+ViT=SiT, validates on CIFAR, STL,puts on arXiv in April. Also submits to PAMI
1/
2) AK posts about SiT
3) Masked AE + ViT from Meta AI, comes out in November, gets nice ImageNet results and get all attention. Not citing SiT

So arXiv does not protect SiT from scooping.
Oh, and PAMI rejects SiT
2/
However, arXiv + social media allow us to at least have this conversation and maybe fix a credit assignment.
Without arXiv as a proof of work, and social media to point out the situation, complete scooping.
3/
Read 4 tweets
Dmytro Mishkin Profile picture
12 Nov
Thanks to @david_picard , I can now formulate why I am for social media.
That is an instrument, where many things depends on you and how good you have done your job.
Writing a good paper is another such thing, but then you are dependent on (random) reviewer choice.
1/
ArXiv is better than the conference in a sense that everyone can see and judge. But it also quite random: your target audience may not check the feed today. However, it is googlable, so not full failure
2/
Now, if we add social media, then we can almost make sure (in long term at least) that target audience will see the paper.
Maybe they will not like it, but they will see it.
3/3
Read 4 tweets
Dmytro Mishkin Profile picture
22 Jul
Let me introduce pixelstitch: simple correspondence annotator based on @matplotlib + jupyter notebook.
Just propvide list of image_fnames and
import CorrespondenceAnnotator.
You can add and erase points, zoom, move, and visualize epipolar geometry, induced by correspondences. 1/
You can install it by
pip install pixelstitch
and the documentation is here:
ducha-aiki.github.io/pixelstitch/
Ofc, powered by nbdev.
All suggestions are welcomed
2/3
Why did I do this? Well, the built-in labelling tools in SfM apps like RealityCapture are nice, but one cannot quickly go through unrelated image pairs.
New artisan datasets for WxBS from me are coming soon,
specifically WxBS-relabeled and EVD 2.0.
3/3
Read 4 tweets
Dmytro Mishkin Profile picture
23 Nov 20
I know, you all have dreamed about the conversion functions between #kornia @kornia_foss and OpenCV. Here they are.

github.com/ducha-aiki/kor…

pip install kornia_moons

Docs are here: ducha-aiki.github.io/kornia-moons/

Powered by @fastdotai and @HamelHusain nbdev
1/3
For example, you can detect ORB features is OpenCV and convert them to kornia lafs with

lafs = laf_from_opencv_ORB_kpts(kps)

Or you can match descriptors on GPU with kornia.feature.match_snn() and transfer to OpenCV with cv2_matches_from_kornia 2/3
The repo is not @kornia_foss "official" in the terms that we don't promise to maintain everything in a timely manner. However, it should work for most of the times :) 3/3
Read 4 tweets
Dmytro Mishkin Profile picture
22 Nov 20
While I am selecting nice pictures for my PhD thesis, let's do a fun visual benchmark of local features on the photos I took myself.

SIFT-HardNet, R2D2, SuperPoint, SuperGlue
1/
Nothing works here, ha :)

SIFT-HardNet, R2D2, SuperPoint, SuperGlue
2/
SIFT-HardNet, R2D2, SuperPoint, SuperGlue

As in 1, only SuperGlue works :)
3/
Read 13 tweets

Did Thread Reader help you today?

Support us! We are indie developers!

This site is made by just two indie developers on a laptop doing marketing, support and development! Read more about the story.

Become a Premium Member ($3/month or $30/year) and get exclusive features!

Become Premium

Too expensive? Make a small donation by buying us coffee ($5) or help with server cost ($10)

Donate via Paypal

Or Donate anonymously using crypto!

Ethereum

0xfe58350B80634f60Fa6Dc149a72b4DFbc17D341E copy

Bitcoin

3ATGMxNzCUFzxpMCHL5sWSt4DVtS8UqXpi copy

Thank you for your support!

Follow Us on Twitter!

Like this author's thread?

Get emails when @ducha_aiki has new unrolls!

Check out other threads from @ducha_aiki!

Read all threads by @ducha_aiki

:(