XMem
NUWA
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
XMem
-
[D] Which open source models can replicate wonder dynamics's drag'n'drop cg characters?
Use Segmentation Model (SAM) combined with Inpainting model (E2FGVI) and Xmem to cut out the live action subject.
-
Track-Anything: a flexible and interactive tool for video object tracking and segmentation, based on Segment Anything and XMem.
Nvm just found the occlusion video on https://github.com/hkchengrex/XMem holy shit
- XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model
-
[D] Most important AI Paper´s this year so far in my opinion + Proto AGI speculation at the end
XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model ( Added because of the Atkinson-Shiffrin Memory Model ) Paper: https://arxiv.org/abs/2207.07115 Github: https://github.com/hkchengrex/XMem
- [D] Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
- Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
-
I trained a neural net to watch Super Smash Bros
Yeah MiVOS would speed up your tagging a lot. I also was curious if you saw XMem which just came out. I found that worked really well too.
-
University of Illinois Researchers Develop XMem; A Long-Term Video Object Segmentation Architecture Inspired By Atkinson-Shiffrin Memory Model
Continue reading | Check out the paper and github link.
-
[R] Unicorn: 🦄 : Towards Grand Unification of Object Tracking(Video Demo)
Have you check XMem?
NUWA
-
How long until we can create full length movies in ai ?
Github: https://github.com/microsoft/NUWA/tree/main/assets/nuwa_infinity/animation
-
[R] NUWA-Infinity, the first paper working on infinite visual synthesis!
Code for https://arxiv.org/abs/2207.09814 found: https://github.com/microsoft/NUWA
- [D] Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
- Most Popular AI Research July 2022 pt. 2 - Ranked Based On GitHub Stars
-
I'm building a timeline for generative image ML models. What's missing?
Microsoft NUWA: https://github.com/microsoft/NUWA
- NUWA Infinity
-
With so many new Text to Image "AI" emerging lately, is it not crazy to speculate about Text to Video?
Microsoft NUWA
-
Have any researchers in the field discussed anything about the prospect of 'text-to-video' - something that's a bit like DALL-E 2, but with a video as the finished output?
NÜWA from Microsoft.
- Art Student here. So about Dalle 2, am I in trouble or should I continue on with my studies? Moreover, what do you think the future holds in store for specific artists (ie comics as opposed to freelance writers as opposed to animators etc) in light of this announcement?
-
Imagine this: complete "fake AI people" are coming, and you didn't even see this coming!
P.S., Lucidrains remade it! AND he's adding an audio transformer to it tomorrow he says! But he needs feedback and someone to train it, I don't think there is enough resources helping this project's training. You can reach him through: https://github.com/microsoft/NUWA
What are some alternatives?
yolov7 - Implementation of paper - YOLOv7: Trainable bag-of-freebies sets new state-of-the-art for real-time object detectors
CogVideo - text and image to video generation: CogVideoX (2024) and CogVideo (ICLR 2023)
flash-attention - Fast and memory-efficient exact attention
DALLE2-video - Direct application of DALLE-2 to video synthesis, using factored space-time Unet and Transformers
hivemind - Decentralized deep learning in PyTorch. Built to train models on thousands of volunteers across the world.
min-dalle - min(DALL·E) is a fast, minimal port of DALL·E Mini to PyTorch
deeplab2 - DeepLab2 is a TensorFlow library for deep labeling, aiming to provide a unified and state-of-the-art TensorFlow codebase for dense pixel labeling tasks.
theseus - A library for differentiable nonlinear optimization
NAFNet - The state-of-the-art image restoration model without nonlinear activation functions.
Cream - This is a collection of our NAS and Vision Transformer work. [Moved to: https://github.com/microsoft/AutoML]
EfficientZero - Open-source codebase for EfficientZero, from "Mastering Atari Games with Limited Data" at NeurIPS 2021.