Martin Danelljan
@MDanelljan
Followers
1,279
Following
347
Media
4
Statuses
118
3D Computer Vision at Apple. Previously Research Group Leader at ETH Zurich.
Zürich, Schweiz
Joined October 2020
Don't wanna be here?
Send us removal request.
Explore trending content on Musk Viewer
PAVILLON DES FOLIES X SAROCHA
• 200779 Tweets
#PavillonDesFoliesxFREEN
• 191497 Tweets
#光る君へ
• 88178 Tweets
BEAUTIFUL FRAGRANCE WITH BUILD
• 66312 Tweets
#せっかくグルメ
• 50727 Tweets
MV TEASER JACK AND JOKER
• 38902 Tweets
#デコピン日村
• 31982 Tweets
John Kerry
• 31782 Tweets
ジャック
• 29065 Tweets
イッテQ
• 25575 Tweets
インライ
• 24375 Tweets
モンスト
• 21074 Tweets
獣神化改
• 14384 Tweets
ツイステ
• 13918 Tweets
ジャミル
• 12624 Tweets
村上誠一郎
• 11973 Tweets
#amici24
• 11095 Tweets
勝平さん
• 10859 Tweets
Happy Birthday Daniel
• 10062 Tweets
Pinned Tweet
I’m happy to share that I’m joining Apple in SF Bay Area as Senior Research Engineer in Computer Vision! I will be working on all things 3D Vision and more.
I’m looking for extremely talented people to work with me and the team on amazing things. Reach out if you are interested!
32
22
515
6 papers accepted to
#ICCV2021
Congratulations to the dedicated and hard-working students! 🎉🏆
1
0
61
2.5 years ago we released the PyTracking library. The large interest has been somewhat overwhelming. Excited to continue making it even better!
We have now released our
#iccv2021
work KeepTrack w/
@chris_mayer_ch
!
paper
PyTracking
3
3
44
Our paper "Deep Reparametrization of Multi-Frame Super-Resolution and Denoising" was accepted at
#iccv2021
as Oral!
Instead of using Attention, we fuse multiple frames through deep unrolled optimization, inspired by classical image restoration.
arXiv:
2
8
34
Code released for our
#CVPR2021
oral paper "DeFlow": A method for unpaired learning of image-to-image translation with normalizing flows.
Excellent master's thesis by
@va_wolf
👏
Also with
@AndreasLugmayr
et al.
arXiv:
code:
1
4
29
So happy for
@alxandrecarlier
that our work DeepSVG was accepted at
#neurips2020
. Generation of vector graphics is a very underexplored subject. In the paper we introduce a new dataset and method.
Check out the amazing repository by
@alxandrecarlier
!
0
4
22
Now you can do unsupervised learning of dense matching and optical flow networks without relying on photometric consistency assumptions!
Check out our
#iccv2021
oral paper on Warp Consistency.
arXiv:
2
3
22
Check out
@prunetruong
and my
#NeurIPS2020
paper proposing the GOCor network module for dense matching. Highly related to Meta-learning and Deep Declarative Networks.
arXiv:
Code (coming soon):
Very excited that our paper 'GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network' got accepted to NeurIPS 2020 !
This is a joint work with
@MDanelljan
, Luc Van Gool and Radu Timofte.
Check out the paper at !
5
25
110
1
2
16
You are welcome to
@prunetruong
and my NeurIPS poster session for "GOCor: Bringing Globally Optimized Correspondence Volumes into Your Neural Network". A meta learning inspired module for SOTA dense correspondences and flow.
Time: Tue 9 am PT / 18.00 CET
0
5
16
Check out the poster session of our NeurIPS 2020 paper "DeepSVG: A Hierarchical Generative Network for Vector Graphics Animation".
Time: Mon 9 pm PT / Tue 06:00 CET
@alxandrecarlier
made an awesome video as well!
0
6
15
See you soon at one of our three posters in the afternoon session at
#CVPR22
!
P75: Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences
P77: Transforming Model Prediction for Tracking
P85: Adiabatic Quantum Computing for Multi Object Tracking
0
3
14
I'm very proud that
@prunetruong
received the
@Apple
AI/ML PhD Fellowship for 2022!
I'm very grateful to receive the
@Apple
AI/ML PhD Fellowship for 2022! This would not have been possible without my incredible mentors and collaborators! Special thanks to my supervisor
@MDanelljan
.
6
5
115
0
0
14
Using probabilistic regression to estimate dense correspondences. Turns out that the most difficult challenge is to learn robust confidences in the unsupervised setting.
Check out our paper and oral presentation at
#CVPR2021
w/
@prunetruong
to see how!
Looking for dense and trustworthy correspondences?
Check out our
#CVPR2021
oral paper w/
@MDanelljan
:
Learning Accurate Dense Correspondences and When to Trust Them
Arxiv:
Code:
Project page:
8
13
86
0
1
13
Our upcoming NTIRE 2021 workshop at CVPR hosts multiple challenges that are currently ongoing. I am co-organizing two completely new ones.
Burst Super-Resolution:
Learning the Super-Resolution Space:
You're welcome to participate!
0
3
12
Check out
@prunetruong
's amazing general framework for dense correspondence estimation!
Includes all our recent works within this topic, and more to come.
📢Code release:
General dense matching library:
- Validation for matching and pose datasets
- Training datasets and pipeline
- Official implementation of GLU-Net (CVPR'20 oral), GOCor (NeurIPS'20), PDC-Net (CVPR'21 oral)
- And much more to come!
1
14
64
0
0
10
Check out our work on improving the mask quality of SAM by just adding a very small amount of parameters and compute!
Segment Anything in High Quality
paper page:
propose HQ-SAM, equipping SAM with the ability to accurately segment any object, while maintaining SAM's original promptable design, efficiency, and zero-shot generalizability. Our careful design reuses and
11
192
993
0
0
11
Thanks to the Apple welcome team and my team mates at the 3D Vision Group for an amazing day of onboarding!
2
0
7
Congratulations Evan 🎉
Very well deserved after all the hard and amazing work! Super proud 😌
What an amazing experience! Thanks
@GMFarinella
and the whole
#icvss2022
team for everything! Such an honor to be awarded, even more as it was together with
@pesarlin
and
@materzynska
!
0
0
20
0
0
3
@OdinLovis
Hey! Really cool stuff. For 3D design, I am not the right person to check with though.
0
0
1