The Power of Context: How Multimodality Improves Image Super-Resolution
Kangfu Mei, Hossein Talebi, Mojtaba Ardakani, Vishal M. Patel @docmilanfar.bsky.social Mauricio Delbracio
tl;dr: condition SR model on RGB+depth+segmentation (which you can predict from RGB)-> PROFIT
arxiv.org/abs/2503.14503
What a lineup! @khipu-ai.bsky.social
khipu.ai#speakers
We are thrilled to announce #Google as Platinum Sponsors for Khipu 2025!
Thank you so much Google for helping make #KHIPU2025 a reality!
We're incredibly grateful to Hopper-Dean Family Foundation, our Diamond Sponsor, for their support of KHIPU 2025! Their partnership is key to making this event a success. #KHIPU2025
#KHIPU2025 starts tomorrow and we are thrilled to have Microsoft AI as a platinum sponsor! Thank you, #MicrosoftAI, for your generous support!
We are so excited to have Apple as a platinum sponsor for #KHIPU2025! Thank you, #Apple, for your valuable support!
You can follow Khipu live streaming at khipu.ai/live
You can follow #KHIPU2025 live, at:
khipu.ai/live/
Going over some old notes from a course by J.M. Morel I found this very nice paper with, what could be, the publication of the first random field manually generated.
"Some informational aspects of visual perception" F Attneave, Psychological review, 1954.
It's an honor to receive this Outstanding recognition for our paper, InDI (w/ @docmilanfar.bsky.social).
We thoroughly enjoyed the process of developing InD, especially the process of building a story from its fundamental principles.
Check out a 15-minute talk: youtu.be/_VfyR9ChOFk
It's an honor to receive this Outstanding recognition for our paper, InDI (w/ @docmilanfar.bsky.social).
We thoroughly enjoyed the process of developing InD, especially the process of building a story from its fundamental principles.
Check out a 15-minute talk: youtu.be/_VfyR9ChOFk
Applications are now open๐๐ผ๐ช๐ผ
๐ฃ Attenti: Early-career academics! Apply for the Google Research Scholar program starting Dec 20th. Get funding for research relevant to Google & build long-term collaborations. Deadline: Jan 27th. This is a global program ๐ research.google/programs-and...
Amazing talk by Arnaud Doucet at #neurips
My favorite. Such good memories.
Yesterday I was very lucky to present in this beautiful seminar room at la universidad de la repรบblica ๐บ๐พ
๐บ๐พ๐๐
Radon Transform (RT) was formulated in 1917 but remained useless in practice until CT scanners were invented in the 60s
But RT isn't just for CTs. It's a sort of generalization of marginals in probability
RT g(p,ฮธ): Shoot rays at ฮธ+90 & offset p, measure line integrals of f(x,y) along the ray
1/n
A photo of the cover of "Learning From Data" book. by Y. Abu-Mostafa, M. Magdon-Ismail and H-T. Lin
Saw some posts out there recommending to skip books... The fundamentals don't change much. Learn the fundamentals from books. This is a great book if you are interested in the fundamentals of Machine Learning:
#KostasThoughts: Core math in many #ComputerScience programs is inadequate for studying #ComputerVision & #MachineLearning. Want to study these subjects? Take (single/multi-variable) calculus, linear algebra, statistics & probability.
Your future self will thank you ๐
๐ฅ
A photo of Richard Feynman, QED "the strange theory of light and matter" book cover.
QED: The Strange Theory of Light and Matter, by R. Feynman. What a gift of making the intricate accessible.
