Just a couple of years ago, I found it hard to believe that vision people were still all working with rectangular bounding boxes. I guess they’ve fixed that now. 🙂

Dr. David Duvenaud doing double duty deriving differential equations and demonstrating how to be a good dad. Full paper: papers.nips.cc/paper/7892-neu…

To understand X I need to review my Chemistry. *2 hours pass*. To understand this part I need to review my Quantum Mechanics. *2 hours pass*. Ok for this I need to review my linear algebra, ordinary/partial diff equations, complex variables, classics mechanics... okay nvm ;’(

PyTorch 1.3 is live!

"PyTorch is becoming the deep learning framework of choice at Microsoft" - Big statement from Microsoft at PyTorch devcon

European Conference on Computer Vision #ECCV2026 #ECCV2020 decisions are now up on OpenReview.

𝐂𝐚𝐧 𝐰𝐞 𝐢𝐧𝐟𝐞𝐫 𝐚𝐧 𝐨𝐛𝐣𝐞𝐜𝐭’𝐬 𝐬𝐡𝐚𝐩𝐞 𝐛𝐲 𝐨𝐛𝐬𝐞𝐫𝐯𝐢𝐧𝐠 𝐢𝐭𝐬 𝐡𝐞𝐚𝐭 𝐟𝐥𝐨𝐰? Check out our recent ECCV paper "𝐒𝐡𝐚𝐩𝐞 𝐟𝐫𝐨𝐦 𝐇𝐞𝐚𝐭 𝐂𝐨𝐧𝐝𝐮𝐜𝐭𝐢𝐨𝐧" to discover how heat reveals form: t.ly/8bGEF

🚨 The 2nd iteration of our #CVPR2025 Foundational Few-Shot Object Detection Challenge is LIVE! Can your model think like an annotator? 🧠💥 Align Vision-Language Models (VLMs) with a few multi-modal examples & win 💰 cash prizes! 🔗 Challenge: eval.ai/web/challenges…

Ground-aerial 3D prediction is tough! Zhiwen(Aaron) Fan's work highlights the struggle for existing models (DUSt3R/MASt3R/VGGT/etc.), indicating that much work still needs to be done in this area. At #CVPR2025, we will be presenting AerialMegaDepth (aerial-megadepth.github.io), a hybrid

Will be presenting our poster shortly at 📍#59! #CVPR2025

Excited to share recent work with Kaihua Chen and Deva Ramanan where we learn to do novel view synthesis for dynamic scenes in a self-supervised manner, only from 2D videos! webpage: cog-nvs.github.io arxiv: arxiv.org/abs/2507.12646 code (soon): github.com/Kaihua-Chen/co…

Check out Nikhil Keetha ‘s latest work that allows flexible input conditioning on top of a VGGT-like architecture! Especially, huge effort in providing data processing for all the datasets + nice code & documentation — this will help the 3D community to build upon this!