Open-Vocabulary SAM


[Paper] [Project Page] [Hugging Face Demo]

Source Code: https://github.com/harboryuan/ovsam?tab=readme-ov-file



join our community:
👉 @deeplearning_ai

PhotoMaker: Customizing Realistic Human Photos via Stacked ID Embedding

[Paper] [Project Page] [Model Card]
[🤗 Demo (Realistic)] [🤗 Demo (Stylization)]

🌠 Key Features:
1. Rapid customization within seconds, with no additional LoRA training.
2. Ensures impressive ID fidelity, offering diversity, promising text controllability, and high-quality generation.
3. Can serve as an Adapter to collaborate with other Base Models alongside LoRA modules in community.

Depth Anything
Unleashing the Power of Large-Scale Unlabeled Data

[Paper] [Code] [Demo]

join our community:
👉 @deeplearning_ai

MLOps Masterclass

🔥Closing registration soon!

Navigating the Landscape of MLOps & LLMOps - Understanding the Synergy

Register Now👇
https://bit.ly/mlops-masterclass

Schedule:
February 24th (Sat) & 25th (Sun), 10AM to 2:30 PM

Highlights of this Masterclass:
▪️MLOps Introduction
▪️MLOps for LLM's (LLMOps)
▪️MLOps and Stages
▪️AWS SageMaker
▪️CI/CD for MLOps
▪️AWS MLOps - Build, Train & deploy ML Model

🔥 Limited Seats Available!

Register Now👇
https://bit.ly/mlops-masterclass

☎️ Contact:
Sarath Kumar
+918940876397 / +918778033930

Awesome-AIGC-3D

A curated list of awesome AIGC 3D papers, inspired by awesome-NeRF.

Source code: https://github.com/hitcslj/awesome-aigc-3d?tab=readme-ov-file

join our community:
👉 @deeplearning_ai

This channels is for Programmers, Coders, Software Engineers.

0- Python
1- Data Science
2- Machine Learning
3- Data Visualization
4- Artificial Intelligence
5- Data Analysis
6- Statistics
7- Deep Learning
8- programming Languages

✅ best channels on Telegram:
https://www.tg-me.com/addlist/8_rRW2scgfRhOTc0

✅ Data Science courses:
https://www.tg-me.com/Python53

EfficientViT - SAM:69x Faster SAM: Multi-Scale Linear Attention for High-Resolution Dense Prediction

1. Channel: @deeplearning_ai

2.Source Code: https://github.com/mit-han-lab/efficientvit

3. Paper: https://arxiv.org/abs/2402.05008

🆔🆔 Magic-Me: Identity-Specific Video 🆔🆔

👉hashtag#ByteDance (+UC Berkeley) unveils VCD for video-gen: with just a few images of a specific identity it can generate temporal consistent videos aligned with the given prompt. Impressive results, source code under Apache 2.0 💙

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Novel Video Custom Diffusion (VCD) framework
✅High-Quality ID-specific videos generation
✅Improvement in aligning IDs-images and text
✅Robust 3D Gaussian Noise Prior for denoising
✅Better Inter-frame correlation / video consistency
✅New modules F-VCD/T-VCD for videos upscale
✅New train with masked loss by prompt-to-segmentation

hashtag#artificialintelligence hashtag#machinelearning hashtag#ml hashtag#AI hashtag#deeplearning hashtag#computervision hashtag#AIwithPapers hashtag#metaverse

👉Channel: @deeplearning_ai
👉Paper https://arxiv.org/pdf/2402.09368.pdf
👉Project https://magic-me-webpage.github.io/
👉Code https://github.com/Zhen-Dong/Magic-Me

🌟 Discover 6DRepNet: The Ultimate Head Pose Estimation Model!

Features:
* State-of-the-art accuracy
* Comprehensive tools for training, testing, and inference
* Easy setup with conda
* Supports multiple datasets

Watch the performance showcase on GitHub for future advancements.

[Source Code] [Paper]

join our community:
👉 @deeplearning_ai

Data Science, Machine Learning & Artificial Intelligence Certification for FREE in 2024

Amazing new year gifts for my subscribers

🎁 Free Data Science Books
🎁 Machine Learning Handwritten Notes
🎁 Python Free Learning Resources
🎁 Learn AI with ChatGPT
🎁 Build Chatbots using LLM
🎁 Learn Generative AI
🎁 Free Coding Certified Courses

Join fast: 👇👇
https://www.tg-me.com/datasciencefun

Send ❤️ if you need more free resources

📢 FREE TRAINING:
Navigating the Landscape of MLOps & LLMOps 🚀

🔥 Join our FREE MLOps course demo and acquire essential skills for AI and data science across Multicloud 🚀

👉 Reserve your seat now:
https://bit.ly/mlops-webinar

🌟 What you'll gain:
1️⃣ ML model deployment techniques on AWS, Azure, GCP & open source.
2️⃣ Efficient data management insights.
3️⃣ Explore the latest MLOps tools.
4️⃣ Real-time interaction with expert instructors.

🚩 Limited spots available! Don't miss out!

👉 Enroll now:
https://bit.ly/mlops-webinar

👥 Share with fellow ML enthusiasts! 🚀✨

Enhance Your AI Insights with AiNews.com

Unlock the full potential of AI with a subscription to AiNews.com, your premier source for cutting-edge AI insights. Stay at the forefront of innovation and trends with content that empowers and informs.

Expand your network by joining our LinkedIn Group, a hub for AI professionals and enthusiasts alike.

Stay Informed. Stay Ahead. With AiNews.com

Introducing ECoDepth: The New Benchmark in Diffusive Mono-Depth

From the labs of IITD, we unveil ECoDepth - our groundbreaking SIDE model powered by a diffusion backbone and enriched with ViT embeddings. This innovation sets a new standard in single image depth estimation (SIDE), offering unprecedented accuracy and semantic understanding.

Key Features:

✅Revolutionary MDE approach tailored for SIDE tasks
✅Enhanced semantic context via ViT embeddings
✅Superior performance in zero-shot transfer tasks
✅Surpasses previous SOTA models by up to 14%

Dive into the future of depth estimation with ECoDepth. Access our source code and explore the full potential of our model.

📖 Read the Paper
💻 Get the Code

#ArtificialIntelligence #MachineLearning #DeepLearning #ComputerVision #AIwithPapers #Metaverse

join our community:
👉 @deeplearning_ai

Neural Bodies with Clothes: Overview

Introduction: Neural-ABC, a cutting-edge parametric model developed by the University of Science & Technology of China, innovatively represents clothed human bodies.

Key Features:

✅Novel approach for modeling clothed human figures.
✅Unified framework accommodating various clothing types.
✅Consistent representation of both body and clothing.
✅Enables seamless modification of identity, shape, clothing, and pose.
✅Extensive dataset with detailed clothing information.

Explore More:
💻Project Details: Discover More
📖Read the Paper: Access Here
💻Source Code: Explore on GitHub

Relevance: #artificialintelligence #machinelearning #AI #deeplearning #computervision

join our community:
👉 @deeplearning_ai

🛞 6Img-to-3D driving scenarios 🛞

👮‍♀️ EPFL (+ Continental) unveils 6Img-to-3D, novel transformer-based encoder-renderer method to create 3D onbounded outdoor driving scenarios with only six pics

🥺 Review: https://shorturl.at/dZ018

🤨 Paper: arxiv.org/pdf/2404.12378.pdf

👉 Project: 6img-to-3d.github.io/

👉 Code: github.com/continental/6Img-to-3D

✅ https://www.tg-me.com/deeplearning_ai

🔍 Introducing UniRef++: Advanced Object Segmentation in Spatial and Temporal Domains
🚀 Key Features:

Unified Model: UniRef++ seamlessly handles segmentation tasks:
✅Referring Image Segmentation (RIS)
✅Few-Shot Segmentation (FSS)
✅Referring Video Object Segmentation (RVOS)
✅Video Object Segmentation (VOS)

Core Component: UniFusion module
✅Integrates reference information efficiently
✅Utilizes flash attention for high efficiency

Compatibility: Acts as a plug-in for foundational models like SAM

🌐 UniRef++ is the official extended implementation from ICCV 2023's UniRef.

Stay tuned for more updates!

👉 Code: https://github.com/FoundationVision/UniRef
🤨 Paper: [Paper link]

✅ https://www.tg-me.com/deeplearning_ai

India's Largest Free Webinar on LLMs especially focused on the recently released LLAMA-3 by Meta.

How do you use these models?
How can you create apps with them?

Join our free workshop on to learn how to use Llama 3 and create apps with it.

Register here: https://www.buildfastwithai.com/events/llama-3-deep-dive

You can connect with Founder;
https://www.linkedin.com/in/satvik-paramkusham/

This Event is especially designed for people interested in the field of AI, ML, GenAI & LLMs.