Christian H

Passion for Cars, Technology and AI

[Laura Leal-Taixe @lealtaixe]

Multi-object tracking methods often feel hacky. It can be frustrating to read a nice paper, only to find a series of "post-processing" hacks to improve the numbers. It is as if the tracking problem could not be solved in a single step... Are you feeling this too? Let's dig👇

[Farid @ai_fast_track]

✨ Diffusion meets Object Detection

📰 DiffusionDet: Diffusion Model for Object Detection

• It formulates object detection as a denoising diffusion process
from noisy boxes to object boxes

• At training, object boxes diffuse from ground-truth boxes to random distribution

[Tony Rosinol @RosinolToni]

A small update on the history of SLAM, and its future :) Last year, NeRFs sparked a new and ongoing era of geo/photometric SLAM!
What lies ahead?
I think some exciting avenues will leverage LLMs, diffusion models, or use light fields as maps!
Same problem, new tools🚀

[Christian H @CHRAnonymous]

@marktenenholtz It’s truly incredible! #PytorchGeometric hasn’t even existed then!

[iwamah @iwamah1]

今まで一般人の記録手段は2D的な物しか無かった所にiPhoneという 3Dスキャンデバイスによって3Dの記録出来るようになったって意外と凄いことだと思ってる
動画はノーカットノー倍速でホテルの部屋の 3Dモデルを作成している所
たった2分でテクスチャ付きの 3Dモデルが出来上がる

[Data Science Dojo @DataScienceDojo]

📂 Cheat sheets for data science and machine learning: https://t.co/YUjwtMgmth

#DataScience #MachineLearning #CheatSheet

[elvis @omarsar0]

These machine learning cheatsheets contain some of the best and well-organized ML content I've come across.

Sometimes, it's just good to understand the concept at a high level and it's context before going deep. This resource helps with that.

https://t.co/ZhEDyBsR8w

[AK @_akhaliq]

LION: Latent Point Diffusion Models for 3D Shape Generation
abs: https://t.co/hZHM2ojPxU
project page: https://t.co/h5vf3l8HEp

[Davide Scaramuzza @davsca1]

Today we did our first experiment in reduced, hyper, and zero gravity! Our goal: study how different g affects self motion estimation in drone pilots in view of future human space missions. A unique opportunity made possible by the @UZHspacehub @UZH_en @NLR_NL w/ @chr_pfeiffer

[Phillip Lippe @phillip_lippe]

Are you interested in learning JAX with Flax? We have translated our popular Deep Learning tutorials on CNNs, GNNs, (Vision) Transformers, and more from PyTorch to JAX+Flax, with considerable speedups for smaller models! Check them out here: https://t.co/x38ZWrjZrT
🧵 1/12

[Bill Peebles @billpeeb]

🎊 New paper!

We train loss-conditional diffusion models of *neural network checkpoints* that learn to optimize.

w/ Radosavovic, Brooks, Efros, Malik

proj: https://t.co/R58P8soLpy
arxiv: https://t.co/9AzqV0koIz
code: https://t.co/1nanm8v2WI

[TensorFlow @TensorFlow]

🎉 NVIDIA and Google are thrilled to announce new milestones and plans to optimize TensorFlow and JAX for the Ampere and recently announced Hopper GPU architectures by leveraging the power of XLA!

Learn more here → https://t.co/mkspSpSu5M

[Orb Amsterdam @OrbAmsterdam]

Merging art with AI 🖼 ⁇ 🖼 ⁇ 🖼

Using the new Outpainting capability of DALL-E 2, we asked @OpenAI to help us imagine how the landscape could look like between famous impressionist paintings from Van Gogh, Monet, Munch and Hokusai.

[Eckler ✦ @daniel_eckler]

AI Art 101 🧵

27 tweets that will 🤯 your brain.

[Nataniel Ruiz @natanielruizg]

Today, along with my collaborators at @GoogleAI, we announce DreamBooth! It allows a user to generate a subject of choice (pet, object, etc.) in myriad contexts and with text-guided semantic variations! The options are endless. (Thread 👇)
webpage: https://t.co/EDpIyalqiK
1/N

[Emad @EMostaque]

Delighted to announce the public open source release of #StableDiffusion!

Please see our release post and retweet! https://t.co/dEsBX7cRHw

Proud of everyone involved in releasing this tech that is the first of a series of models to activate the creative potential of humanity

[AI Pub @ai__pub]

// Stable Diffusion, Explained //

You've seen the Stable Diffusion AI art all over Twitter.

But how does Stable Diffusion _work_?

A thread explaining diffusion models, latent space representations, and context injection:

1/15

[Matthias Niessner @MattNiessner]

Check out Texturify at #ECCV2022!

Our graph generative model produces high-quality textures on meshes, trained entirely unsupervised! For training, we only need ShapeNet (no textures) and a set of real images. The texture model is then learned through differentiable rendering.

[Ego4D @ego4_d]

Ego4D challenges are now open for ECCV’22! 16 tracks with $100K in prizes! Deadline to submit: Sept 18. What happened at the CVPR challenges you ask? Read on for a quick summary:

[Christian H @CHRAnonymous]

@davsca1 @RosinolToni @supitalp @DanielGehrig6 Thank you for open sourcing this to provide more insight into the field of event cameras for many research labs to work on this exciting new topic!