chrisohrstrom.bsky.social
Christoffer Koo Øhrstrøm
@chrisohrstrom.bsky.social
110 followers 420 following 3 posts
PhD student at DTU 🇩🇰 Doing research at the intersection of deep learning, event cameras/neuromorphic vision, multi-modal models, and robotics.
Posts Media Videos Starter Packs
Reposted by Christoffer Koo Øhrstrøm
lanalpa.bsky.social
Lazaros Nalpantidis @lanalpa.bsky.social · Jan 8
Can Dynamic Neural Networks boost Computer Vision and Sensor Fusion?
We are very happy to share this awesome collection of papers on the topic!
zioictus.bsky.social
Fabio Montello @zioictus.bsky.social · Jan 8
First little project of the year: an awesome collection of papers on Dynamic Neural Networks for Computer Vision and Sensor Fusion!

Each paper comes with a brief summary and code link.

👉 github.com/DTU-PAS/awes...
GitHub - DTU-PAS/awesome-dynn-for-cv: Awesome collection of DyNN papers for Computer Vision and Sensor Fusion applications :sparkles:
Awesome collection of DyNN papers for Computer Vision and Sensor Fusion applications :sparkles: - DTU-PAS/awesome-dynn-for-cv
github.com
2 6
chrisohrstrom.bsky.social
Christoffer Koo Øhrstrøm @chrisohrstrom.bsky.social · Dec 18
True. Not much of an issue on small codebases. Mostly just feels better with a snappier formatter for those.
2
chrisohrstrom.bsky.social
Christoffer Koo Øhrstrøm @chrisohrstrom.bsky.social · Dec 18
black is great, but I prefer Ruff because of speed and it is also a really nice linter. docs.astral.sh/ruff/
Ruff
An extremely fast Python linter and code formatter, written in Rust.
docs.astral.sh
1 5
Reposted by Christoffer Koo Øhrstrøm
iscienceluvr.bsky.social
Tanishq Mathew Abraham @iscienceluvr.bsky.social · Dec 10
Inventors of flow matching have released a comprehensive guide going over the math & code of flow matching!

Also covers variants like non-Euclidean & discrete flow matching.

A PyTorch library is also released with this guide!

This looks like a very good read! 🔥

arxiv: arxiv.org/abs/2412.06264
1 26 110
chrisohrstrom.bsky.social
Christoffer Koo Øhrstrøm @chrisohrstrom.bsky.social · Nov 28
Maybe this is it? arxiv.org/abs/2409.10202 @jakubgregorek.bsky.social
SteeredMarigold: Steering Diffusion Towards Depth Completion of Largely Incomplete Depth Maps
Even if the depth maps captured by RGB-D sensors deployed in real environments are often characterized by large areas missing valid depth measurements, the vast majority of depth completion methods st...
arxiv.org
1 1 8