
Kosta Derpanis
@CSProfKGD
Followers
66K
Following
71K
Media
5K
Statuses
34K
#CS Assoc Prof @YorkUniversity, #ComputerVision Scientist Samsung #AI, @VectorInst Faculty Affiliate, TPAMI AE, @ELLISforEurope Member #ICCV2025 Publicity Chair
Toronto, Ontario
Joined August 2015
Lecture slides for my "Introduction to #ComputerVision" and "#DeepLearning in Computer Vision" courses. š Gaussian Splatting.š Flow Matching . The included videos do not contain voiceovers yet, planned for a future revision.
3
72
405
RT @SwetaMahajan1: Introducing the speakers for the eXCV workshop @ICCVConference. Get ready for stimulating and insightful talks and discā¦.
0
4
0
RT @roydanroy: The Department of Statistical Sciences in the Faculty of Arts and Science at the University of Toronto invites applicationsā¦.
0
10
0
RT @docmilanfar: For better consistency and fewer artifacts in im2im diffusion models, consider Kernel Density Steering (KDS): It is infereā¦.
0
30
0
RT @ICCVConference: The deadline for camera-ready paper and copyright submission for #ICCV2025 is Friday, August 1st, 2025 @ 11:59 Pacificā¦.
0
7
0
RT @_albertgu: I converted one of my favorite talks I've given over the past year into a blog post. "On the Tradeoffs of SSMs and Transforā¦.
0
109
0
RT @dimadamen: How to make 3D fundamental to all aspects of computer vision?.A Vedaldi @Oxford_VGG with a brilliant tutorial this morning @ā¦.
0
3
0
RT @CSProfKGD: #presentationzen by Garr Reynolds @presentationzen changed my approach to preparing and giving presentations, both lecturesā¦.
0
6
0
RT @jbhuang0604: Why is the "Title and Content" slide layout BAD?. Most people prepare their presentation from this default layout. I usedā¦.
0
14
0
RT @dimadamen: Giving a tutorial @icvss is special - you could inspire the brightest upcoming researchers in the field, eager to learn andā¦.
0
1
0
RT @3DVconf: Introducing your #3DV2026 General Chairs!.@ManolisSavva @VcaiMpi @akanazawa. General Chairs oversee and coordinate every facetā¦.
0
4
0
RT @liyuan_zz: Point maps have become a powerful representation for image-based 3D reconstruction. What if we could push point maps even fuā¦.
0
57
0
RT @du_yilun: Excited to share Energy-Based Transformers (EBTs), which allows you to implement system 2 thinking in any modality! . EBTs foā¦.
0
131
0