AI with Papers - Artificial Intelligence & Deep Learning – Telegram

AI with Papers - Artificial Intelligence & Deep Learning

@AI_DeepLearning

15.2K subscribers

135 photos

247 videos

14 files

1.31K links

All the AI with papers. Every day fresh updates about #DeepLearning, #MachineLearning, LLMs and #ComputerVision

Curated by Alessandro Ferrari | https://www.linkedin.com/in/visionarynet/

#artificialintelligence #machinelearning #ml #AI

Download Telegram

About

Blog

Apps

Platform

AI with Papers - Artificial Intelligence & Deep Learning

15.2K subscribers

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6871363962756222976-D7GP

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai… | 22 comments

🧁🧁The new SOTA in RVOS (semantic segmentation + captions) just open-sourced🧁🧁

👉RVOS task involves segmentation of a text-referred object instance in the… | 22 comments on LinkedIn

431 views08:28

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6871716302273212416-URYj

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai…

🥝🥝HyperStyle, a hypernetwork to modulate StyleGAN for Hi-Fi inversion, just open-sourced🥝🥝

👉Inversion of real images into StyleGAN’s latent space is an…

425 views07:50

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/feed/update/urn:li:activity:6872820895182856192/

👽👽SAFA, a novel structure-aware neural generator, just open-sourced - Alessandro Ferrari on LinkedIn

👽👽SAFA, a novel structure-aware neural generator, just open-sourced👽👽

👉GAN has made great progress on the face animation task. However, without knowing...

499 views09:14

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_3d-ai-artificialintelligence-activity-6874609426234449920-VUXG

Alessandro Ferrari on LinkedIn: #3d #ai #artificialintelligence #machinelearning #deeplearningai… | 10 comments

🔴🟢 Berkeley unveils PHALP, a novel 3D tracking by appearance, location & pose 🔴🟢

👉Novel approach for tracking people in monocular videos by predicting… | 10 comments on LinkedIn

527 views07:25

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_deeplearning-ai-artificialintelligence-activity-6874990579172864000-snJB

Alessandro Ferrari on LinkedIn: #Deeplearning #AI #artificialintelligence

🚶‍♂️🚶🚶‍♀️ Do pedestrians pay attention? 🚶‍♂️🚶🚶‍♀️

👉 Humans rely on eye contact for fast/efficient communication with nearby people. Autonomous...

509 views08:39

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_gpu-ai-artificialintelligence-activity-6875366940328759296-C1DP

🍉🍉 Plenoxel: Radiance Fields 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 neural networks 🍉🍉 - Alessandro Ferrari on LinkedIn

🍉🍉 Plenoxel: Radiance Fields 𝘄𝗶𝘁𝗵𝗼𝘂𝘁 neural networks 🍉🍉

👉Berkeley unveils Plenoxel, a view-dependent sparse voxel model that can optimize ...

516 views09:37

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6876516773701709824-nHk3

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai…

🍠🍠 ViT Deep features for Co-segmentation, Part Co-segmentation, and Semantic Correspondences 🍠🍠

👉“Deep Features” extracted from the activation of layers…

579 views13:45

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6876801322222444544-PtSe

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai… | 16 comments

🥭🥭Real-ESRGAN: Super-Resolution with pure Synthetic Data🥭🥭

👉Single image super-resolution topic aims at reconstructing a high-resolution image from its… | 16 comments on LinkedIn

568 views08:37

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_musk-deepfake-artificialintelligence-activity-6877894830790381568-FzO6

Alessandro Ferrari on LinkedIn: #musk #deepfake #artificialintelligence #machinelearning #deeplearningai… | 11 comments

😮The Chinese #Musk doppelganger: #deepfake or… | 11 comments on LinkedIn

574 views09:01

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6878269063550824448-mbZM

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai…

🤩🤩The SOTA in video instance segmentation is insane (every day better)🤩🤩

👉SeqFormer is the frustratingly simple model for video instance segmentation…

604 views09:49

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-ai-artificialintelligence-activity-6879051306888151040-a2Jh

[Video] Alessandro Ferrari on LinkedIn: #ai #ai #artificialintelligence #machinelearning #deeplearningai… | 20 comments

✂️🧴The #AI Barbershop source code is out! 🧴✂️

👉Even though recent work on GANs enables synthesis of realistic hair or faces, it remains difficult to… | 20 comments on LinkedIn

623 views13:35

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/feed/update/urn:li:activity:6882235940719407104/

🐸🐸 StyleGAN-V: new SOTA in Continuous Video Generation is magic 🐸🐸 | Alessandro Ferrari

🐸🐸 StyleGAN-V: new SOTA in Continuous Video Generation is magic 🐸🐸

👉StyleGAN-V extends the recent paradigm of neural representations to the video generation domain. KAUST & #Snap show with this model that is possible to generate arbitrarily long clips at…

624 views08:31

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-ai-artificialintelligence-activity-6884045792156401664-XL6X

🤹‍♀️🤹‍♂️“Splice" #AI: painting the structure of an image with the appearance of another one🤹‍♀️🤹‍♂️ | Alessandro Ferrari

🤹‍♀️🤹‍♂️“Splice" #AI: painting the structure of an image with the appearance of another one🤹‍♀️🤹‍♂️

👉WAIC unveils an #AI to generate objects in a source structure image “painted” with the visual appearance of their semantically related objects in a target…

636 views08:22

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_artificialintelligence-machinelearning-deeplearningai-activity-6888047539321368576-xM6q

😮🤩 WebToonMe project made my day 😮🤩 | Alessandro Ferrari | 13 comments

😮🤩 WebToonMe project made my day 😮🤩

- Webtoon Me: https://lnkd.in/dSi2JjvS
- Webtoon Painter: https://lnkd.in/d-2_Y3Bp
- Company: https://lnkd.in/dcVbemiz

#artificialintelligence #machinelearning #deeplearningai #deepneuralnetworks #neuralnetworks #ml …

697 views09:41

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6888865640073977857-INbR

😵‍💫🤪SeamlessGAN, endless texture generator, is hypnotic😵‍💫🤪 | Alessandro Ferrari

😵‍💫🤪SeamlessGAN, endless texture generator, is hypnotic😵‍💫🤪

👉Real-time graphics requires HQ textured materials to convey realism in virtual env. Generating textures is challenging as they need to be realistic, seamlessly tileable, and low-memory.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:…

747 views15:34

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_computervision-ai-artificialintelligence-activity-6889245549426552832-BoEf

🦚🦚ELSED: the best/fastest line detector ever🦚🦚 | Alessandro Ferrari | 11 comments

🦚🦚ELSED: the best/fastest line detector ever🦚🦚

👉Detecting local features, such as corners, segments or blobs, is the first step in the pipeline of many #computervision applications. Its speed is crucial for real-time applications.

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅ELSED: Enhanced…

👍1

835 views16:48

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6889481820132401152-1VKe

🦎🦎GANmouflage: learn to non-detecting objects🦎🦎

👉GANmouflage - Alessandro Ferrari on LinkedIn | 23 comments

🦎🦎GANmouflage: learn to non-detecting objects🦎🦎

👉GANmouflage by UMich & Berkeley learns to camouflage 3D objects within scenes. Given an object’s... 23 comments on LinkedIn

🤩1

899 views08:23

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6889843695810560000-fvYL

Alessandro Ferrari on LinkedIn: #ai #artificialintelligence #machinelearning #deeplearningai… | 19 comments

👕👚Re-rendering human fashion style with GAN👚👕

👉VT + Adobe are open sourcing a new algorithm for generating detail-preserving and photo-realistic… | 19 comments on LinkedIn

❤1

1.05K views08:24

AI with Papers - Artificial Intelligence & Deep Learning

https://www.linkedin.com/posts/visionarynet_ai-artificialintelligence-machinelearning-activity-6890692463867346944-CLTZ

Alessandro Ferrari on LinkedIn: #AI #artificialintelligence #machinelearning

😈😈STIT: a novel GAN-based, temporal consistent, video facial editor😈😈

👉The ability of GANs to encode rich semantics is well-known. However, replicating...

👍1

1.18K views16:35

AI with Papers - Artificial Intelligence & Deep Learning

AI with Papers - Artificial Intelligence & Deep Learning

🀄 Drag-GAN: user-friendly image-manipulation 🀄 👉 Manual deforming of (real and generated) images over pose, shape, expression and layout. 😎Review https://bit.ly/3BFyXlR 😎Paper arxiv.org/pdf/2305.10973.pdf 😎Project vcai.mpi-inf.mpg.de/projects/DragGAN…

🔥🔥 Source Code IS OUT! 🔥🔥

😎 More: https://t.ly/ZddLl

🔥🔥 Source Code of Drag-GAN IS OUT! | Alessandro Ferrari | 40 comments

🔥🔥 Source Code of Drag-GAN IS OUT! 🔥🔥

👉Manual deforming of (real and generated) images over pose, shape, expression and layout. Source Code just released a few hours ago 👇

𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Max Planck + MIT + #Google AR/VR = 🤯
✅Supervising handle points to move…

🔥25😱6❤3🥰1🤯1

6.99K viewsedited 07:20