🥛🥛HAMSTER: Hierarchical VLA Manipulation🥛🥛
👉#Nvidia unveils HAMSTER: novel Hierarchical VLA architecture to enable robotic manipulation with semantic, visual & geometric generalization trained on easy to collect, off-domain data. Source Code announced💙



𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:

✅Hier. Action Models w/ SeparaTEd Path Represent.

✅Fine-tuned VLMs -> to low-level 3D policy models

✅A fully open-sourced enabler for VLM-action models

✅Abundant OOD data for improving real-world control



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



👉Discussion https://lnkd.in/dMgakzWm

👉Paper https://arxiv.org/pdf/2502.05485

👉Project https://hamster-robot.github.io/

👉Repo TBA

🚀 3DGazeNet: Revolutionizing Gaze Estimation with Weak-Supervision! 🌟

Key Features:
🔹 Advanced Neural Network: Built on the robust U2-Net architecture.
🔹 Comprehensive Utilities: Easy data loading, preprocessing, and augmentation.
🔹 Seamless Integration: Train, test, and visualize with simple commands.

Demo Visualization:Visualize the demo by configuring your video path in main.py and showcasing the power of 3DGazeNet.

Pretrained Weights:Quick start with our pretrained weights stored in the weights folder.

💻Source Code: https://github.com/Shohruh72/3DGazeNet
📖Read the Paper: Access Here


#3DGazeNet #GazeEstimation #AI #DeepLearning #TechInnovation

Join us in pushing the boundaries of gaze estimation technology with 3DGazeNet!

🔥🔥Distill-Any-Depth: new SOTA MDE🔥🔥

👉Distill-Any-Depth is the new SOTA monocular depth estimation model trained with a novel knowledge distillation. Source Code, pre-trained models & f-demo released💙

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Authors: ZJUT, WestLake University, LZU & NTU
✅Multiple D-normalization on pseudo-label distillation
✅Proposing novel Cross-Context Distillation approach
✅Introducing new multi-teacher distillation framework
✅Pre-trained Models and code released under MIT

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

👉Discussion https://lnkd.in/dMgakzWm
👉Paper arxiv.org/pdf/2502.19204
👉Repo https://lnkd.in/dPtxNrQh
🤗Demo https://lnkd.in/d2TMPf4b

🚀 Introducing L2CS-Net: Fine-Grained Gaze Estimation 👀✨

🔗 GitHub Repo: Star ⭐ the Repo

🔥 Key Features:
✅ Fine-grained gaze estimation with deep learning
✅ Supports Gaze360 dataset
✅ Train with Single-GPU / Multi-GPU
✅ Demo for real-time visualization

📌 Quick Start:
🗂️ Prepare dataset
🏋️ Train (python main.py --train)
🎥 Video Infernece (python main.py --demo)

🌟 Support Open Source! Star ⭐ & Share!
🔗 GitHub Repo: L2CSNet

#AI #DeepLearning #GazeEstimation #L2CSNet #OpenSource 🚀

🚀 Introducing L2CS-Net: Fine-Grained Gaze Estimation 👀✨

🔗 GitHub Repo: Star ⭐ the Repo

🔥 Key Features:
✅ Fine-grained gaze estimation with deep learning
✅ Supports Gaze360 dataset
✅ Train with Single-GPU / Multi-GPU
✅ Demo for real-time visualization

📌 Quick Start:
🗂️ Prepare dataset
🏋️ Train (python main.py --train)
🎥 Video Infernece (python main.py --demo)

🌟 Support Open Source! Star ⭐ & Share!
🔗 GitHub Repo: L2CSNet

#AI #DeepLearning #GazeEstimation #L2CSNet #OpenSource 🚀

🚀 Refactored HRNet Now Live! 🚀

🔥 Supercharge your computer vision projects with high-resolution HRNet models – fully refactored for easy training/testing!

✅ Multiple ImageNet-pretrained models
✅ Lightning-fast setup
✅ Top-tier accuracy

👉 Check it out & ⭐️ Star the repo if you find it useful!
GitHub: Shohruh72/HRNet

#AI #DeepLearning #OpenSource

@deeplearning_ai

🚀 3DGazeNet: Next-Gen Gaze Estimation! - get instant results with just one click.

Discover how to train powerful gaze estimation models using only synthetic data and weak supervision—no huge real-world datasets needed.
Perfect for AR/VR, HCI, and beyond.
Cutting-edge, open-source, and ready for your next project!

👉 Try it now: https://github.com/Shohruh72/3DGazeNet

#DeepLearning #GazeEstimation #AI

@deeplearning_ai

🐉 #DoubleDragon with #AI 🐉

👉How Double Dragon would look like in real life? Each character has been transformed with #AI to capture their style, fighting spirit, and charisma, as if they had stepped right out of the game’s streets into the real world. AUDIO ON. Damn romantic💙

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

👉Post https://t.ly/0IpER
👉Channel http://www.youtube.com/@iaiaoh84

🐼Pixel-Dense Embedding of Motion🐼

👉FlowFeat is a novel high-resolution and multi-task feature representation that embeds a distribution of plausible apparent motions, or motion profiles. Repo available under 💙

#artificialintelligence #AI #deeplearning #AIwithPapers

👉Review https://t.ly/aUx_U
👉Paper arxiv.org/pdf/2511.07696
👉Project tum-vision.github.io/flowfeat
👉Repo github.com/tum-vision/flowfeat

🕶️ Seeing without Pixels 🕶️

👉Is it possible to perceive a video’s content without seeing its pixels, just from the camera trajectory? #Google Deepmind (+ UTexas) is the first to systematically investigate this seemingly implausible question💙



𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:

✅CamFormer: pre-trained dedicated trajectory encoder

✅Proposing a novel contextualized trajectory encoding

✅Scenarios: egocentric & exocentric (third-person)

✅Outperforming "heavy" vision models in key scenarios



#artificialintelligence #AI #deeplearning #AIwithPapers #LLM



👉Discussion https://lnkd.in/dMgakzWm

👉Paper https://arxiv.org/pdf/2511.21681

👉Project https://sites.google.com/view/seeing-without-pixels

🔥 New #AI Startups in 2026? 🔥

In 2026, which area would you focus on?
🤖Agents → workflows, copilots, etc.
🏭Vertical AI → Pharma, Automotive, Energy ...
🧠Infrastructure → MLOps, Security, Cost Control ...
🎨AI for Creators/Media → Video, avatars, contents ...

Please, help me understanding what's next with this poll on LinkedIn :)

https://www.linkedin.com/posts/visionarynet_ai-ai-deeplearning-activity-7415377341779996672-sQO1

LUV U \m/

- Sent via TeleFeed

🍑 Metric Anything is out 🍑

👉Metric Anything (Li Auto inc.) is a simple and scalable pretraining framework that learns metric depth from noisy, diverse 3D sources without manually engineered prompts, camera-specific modeling, or task-specific architectures. Impressive work. Code announced 💙

👉Review https://t.ly/54Ccr
👉Paper arxiv.org/pdf/2601.22054
👉Project metric-anything.github.io/metric-anything-io/
👉Repo github.com/metric-anything/metric-anything

- Sent via TeleFeed

🍿🍿Dawn of Generative Cinematography🍿🍿



🟩#TheOdyssey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture.



👉Meanwhile, #AI research is heading in the exact opposite direction.



🟩A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere.



🟩Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards.



👉And this fundamentally changes what cinematography means.



🟩For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever.



🟩A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized.



🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been?

The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional.



👉The first step towards the generative cinematography.



#deeplearning #computervision #AIwithPapers



👉Discussion https://lnkd.in/dMgakzWm

👉Paper arxiv.org/pdf/2607.24591

👉Project yixuanli98.github.io/cameraanything/

👉Repo github.com/yixuanli98/CameraAnything

• Sent via TeleFeed

🍿Dawn of Generative Cinematography🍿

🟩 The Odissey by Christopher Nolan was shot entirely on IMAX 70mm. It feels almost romantic: massive cameras, film stock, premium lenses, and an obsessive pursuit of the highest possible quality at the moment of capture.

👉 Meanwhile, #AI research is heading in the exact opposite direction.

🟩 A pre-print paper released today, "Camera Anything", demonstrates something that sounded like science fiction just a few years ago: you film a scene once... and then you can virtually reposition the camera anywhere.

🟩 Want a close-up? A drone shot? A ground-level perspective? A side angle? A cinematic tracking shot? You no longer decide where to place the camera during filming. You decide afterwards.

👉 And this fundamentally changes what cinematography means.

🟩 For more than a century, filmmakers have had to make irreversible decisions on set. Camera placement, focal length, movement, framing, etc. These choices became part of the recorded footage forever.



🟩 A scene becomes a 3D representation that can be "re-shot" endlessly from viewpoints that never physically existed. We simply capture "raw" data from which the final result is reconstructed or customized.



🟩Five years from now, will we still talk about shooting a movie? Or will we simply capture a scene and decide later where the camera should have been?

The irony is fascinating. While Nolan reminds us how extraordinary a 70mm camera can be, AI is quietly suggesting that, soon, the camera itself will be optional.



👉The first step towards the generative cinematography.



#deeplearning #computervision #AIwithPapers



👉Discussion https://lnkd.in/dMgakzWm

👉Paper arxiv.org/pdf/2607.24591

👉Project yixuanli98.github.io/cameraanything/

👉Repo github.com/yixuanli98/CameraAnything

• Sent via TeleFeed

🔥🔥 Marigold V2 is out 🔥🔥

👉Marigold V2 is out: depth, (impressive) see-through depth, surface normals, albedo, and other dense modalities. SOTA results. Repo under Apache 2.0💙

#AI #deeplearning #AIwithPapers

👉Review https://lnkd.in/p/eKM44yDQ
👉Paper https://arxiv.org/pdf/2609.08084
👉Repo https://github.com/huawei-bayerlab/marigold-v2
👉Project https://huggingface.co/spaces/huawei-bayerlab/marigold-v2-web

• Sent via TeleFeed