Kosta Derpanis

#CS Associate Prof @YorkUniversity, #ComputerVision Researcher, @VectorInst Affiliate, @UofT status only, @ELLISforEurope Member

[Kosta Derpanis @CSProfKGD]

I’ve launched 2 new course websites for my Introduction to #ComputerVision and #DeepLearning in Computer Vision courses.

🆕 Gaussian Splatting
🆕 Flow Matching
🆕 Sparse Autoencoders
🆕 Lecture Notes (work in progress)

The videos don’t include voiceovers, but that’s coming in a future revision 🤞

Share your feedback in the thread.

[Jitendra MALIK @JitendraMalikCV]

3D/4D reconstruction is one of the great achievements of computer vision. With roots in photogrammetry, multi-view geometry was much studied (e.g. Hartley & Zisserman). In the last decade, it was successfully combined with deep learning. Shape priors which come from recognition got incorporated (e.g. for humans, in HMR) and recent systems like VGGT and SAM 3D can do amazing stuff. This progress is directly relevant for robotics, which (duh) operates in the 3D world. Many robotics papers in the learning era weren't exploiting 3D structure, which IMHO is just wasting valuable signal. But there has been a strong real2sim2real tradition for years e.g. here are two projects from my group (and there are many others, I am not claiming exclusivity). I am glad that people have rediscovered this capability with Astra. But please do give credit to human researchers, not just AI models. https://t.co/OeBSOfO6Sg ,
https://t.co/7ZIrP8SPU1

[Sameh Khamis @sameh_khamis]

Back in my day moment! was curious to see how methods & tasks in computer vision evolved since I joined.
CNNs came out of nowhere, RNNs / GANs had their moment, and now transformers dominate, RL rising.
Tasks had their biggest change in 2024 with segmentation losing the throne.

[Kosta Derpanis @CSProfKGD]

What should we be at now, @OriolVinyalsML? 😅

[Lucas Beyer (bl16) @giffmana]

omg I love the term "slop grenade" it's perfect thx @tobi

[Kosta Derpanis @CSProfKGD]

I’ve launched 2 new course websites for my Introduction to #ComputerVision and #DeepLearning in Computer Vision courses.

🆕 Gaussian Splatting
🆕 Flow Matching
🆕 Sparse Autoencoders
🆕 Lecture Notes (work in progress)

The videos don’t include voiceovers, but that’s coming in a future revision 🤞

Share your feedback in the thread.

[Kosta Derpanis @CSProfKGD]

@ziv_ravid “Submitted”

[Kosta Derpanis @CSProfKGD]

@apratimbh Even bigger … the rest of my life 😉💪

[Kosta Derpanis @CSProfKGD]

Good morning #Toronto!

#Project51

[Denny Zhou @denny_zhou]

ICLR 2027 has received more submissions than all previous years (2013–2026) combined

[Kosta Derpanis @CSProfKGD]

Note the helmet @y_m_asano 😉

[Kosta Derpanis @CSProfKGD]

@menhguin I was waiting for that 🤓

[Kosta Derpanis @CSProfKGD]

@letyrodri 😅

[Kosta Derpanis @CSProfKGD]

@PlisSergey @ieee_mlsp Hotlanta is very tempting 😉

[Kosta Derpanis @CSProfKGD]

@roeiherzig @HildeKuehne Appears to follow the lottery logic that you have to play to win. People have lost their sense of holding back incomplete or ill-fitting work.

[Kosta Derpanis @CSProfKGD]

@YuXiang_IRVL @RoboticsSciSys From one publicity chair to another: thank you for your service 🫡

[Yu Xiang @YuXiang_IRVL]

Nice milestone for @RoboticsSciSys: 10K followers!

Glad to have served as Publicity Chair for RSS 2026 and helped share the exciting work from our community. Now it’s time to hand the account over to the next Publicity Chair. Looking forward to seeing RSS continue to grow!

[Kosta Derpanis @CSProfKGD]

@bibek_poudel_ 😂

[Kosta Derpanis @CSProfKGD]

I predict a crime spree is coming.
Nothing stolen, just random #ICLR2027 submissions left behind. Stay vigilant 👀

[Georgia Chalvatzaki @GeorgiaChal]

https://t.co/yGjRDKdY0q