AI with Papers - Artificial Intelligence & Deep Learning
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
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿช› AgileAvatar: HQ stylized 3D #Avatar ๐Ÿช›

๐Ÿ‘‰#ByteDance unveils a novel self-supervised framework for #3D avatars

๐Ÿ˜ŽReview https://bit.ly/3kaOAw6
๐Ÿ˜ŽProject ssangx.github.io/projects/agileavatar
๐Ÿ˜ŽPaper ssangx.github.io/pubs/2022-SIGGRAPHAsia-AgileAvatar.pdf
๐Ÿ‘9โค3
๐Ÿ”ฅ #Nvidia GC ViT Large -> updated! ๐Ÿ”ฅ

๐Ÿ‘‰The new SOTA (with large margin) across image classification, detection & semantic segmentation!

๐Ÿ˜ŽReview https://bit.ly/3W4ChyF
๐Ÿ˜ŽCode github.com/NVlabs/GCViT
๐Ÿ˜ŽPaper arxiv.org/pdf/2206.09959.pdf
๐Ÿ”ฅ6
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŽ›๏ธ VecGAN: DETAILED Face Manipulation ๐ŸŽ›๏ธ

๐Ÿ‘‰ VecGAN: SOTA I2I for facial editing with interpretable latent directions

๐Ÿ˜ŽReview https://bit.ly/3GGNUpZ
๐Ÿ˜ŽProject yusufdalva.github.io/vecgan/
๐Ÿ˜ŽCode github.com/yusufdalva/VecGAN
๐Ÿ˜ŽPaper arxiv.org/pdf/2207.03411.pdf
๐Ÿคฏ6
๐ŸงŠ HOTCOLD: Thermal Adv-Fashion ๐ŸงŠ

๐Ÿ‘‰A novel physical attack for IR cams via wearable temperature-sensitive patches

๐Ÿ˜ŽReview https://bit.ly/3k8mt0B
๐Ÿ˜ŽPaper arxiv.org/pdf/2212.05709.pdf
๐Ÿ˜ŽCode github.com/weihui1308/HOTCOLDBlock
๐Ÿคฉ5
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ‘› New Task in #AI: Domain Expansion ๐Ÿ‘›

๐Ÿ‘‰#Adobe on augmenting the space a model can generate, without overriding its original behavior

๐Ÿ˜ŽReview https://bit.ly/3ZCtwPA
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.05225.pdf
๐Ÿ˜ŽProject yotamnitzan.github.io/domain-expansion
๐Ÿ˜ŽCode github.com/adobe-research/domain-expansion
๐Ÿ‘2๐Ÿ˜ฑ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ MMEditing: SOTA toolbox for #AI ๐Ÿ

๐Ÿ‘‰An open-source image/video editing toolbox based on #PyTorch

๐Ÿ˜ŽReview https://bit.ly/3k4cmK8
๐Ÿ˜ŽProject github.com/open-mmlab/mmediting
๐Ÿ”ฅ12๐Ÿ‘4
๐Ÿ“ถ Dense Pose from WiFi ๐Ÿ“ถ

๐Ÿ‘‰AI able to map phase/amplitude of WiFi signals for human sensing application

๐Ÿ˜ŽReview https://bit.ly/3QDeFQC
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.00250.pdf
๐Ÿคฏ33๐Ÿ”ฅ5๐Ÿ‘2๐Ÿ˜ฑ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿต๏ธ Instant-NeRF Artists Gallery ๐Ÿต๏ธ

๐Ÿ‘‰A gallery of beautiful scenes powered by the #NVIDIA Instant-NeRF

๐Ÿ˜ŽReview https://bit.ly/3XxV9au
๐Ÿ˜ŽGallery www.nvidia.com/en-us/research/ai-art-gallery/instant-nerf
๐Ÿ”ฅ7๐Ÿ‘2๐Ÿฅฐ2โค1
๐Ÿชท Saliency Detection by/for Impaired ๐Ÿชท

๐Ÿ‘‰A novel dataset using images taken by visually impaired people. Suitable for (big object/text) saliency detectors

๐Ÿ˜ŽPaper arxiv.org/pdf/2301.05323.pdf
๐Ÿ˜ŽData vizwiz.org/tasks-and-datasets/salient-object-detection
๐Ÿ˜ŽCode vizwiz.org/wp-content/uploads/2023/01/sod_mask_example.txt
๐Ÿ”ฅ10
๐Ÿงช YOLOv6 v3.0 is out! ๐Ÿงช

๐Ÿ‘‰Meituan open-sourced YOLOv6 v3.0: many novel enhancements on architecture & training scheme. New SOTA on COCO!

๐Ÿ˜ŽReview https://bit.ly/3wbj7wC
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.05586.pdf
๐Ÿ˜ŽCode github.com/meituan/YOLOv6
๐Ÿ”ฅ7๐Ÿคฃ7๐Ÿพ3
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿฅซ Plug 'n' play self-checkout ๐Ÿฅซ

๐Ÿ‘‰#Google's new shelf-checking #AI: recognizing billions of products, even purchased/moved

๐Ÿ˜ŽReview https://bit.ly/3J58hQe
๐Ÿ˜ŽNews https://cloud.google.com/blog/transform/nrf-2023-google-cloud-big-show-big-moment-hybrid-retail
๐Ÿคฏ8๐Ÿ‘7
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŠ GLIGEN: Grounded T2I Diffusion ๐ŸŠ

๐Ÿ‘‰New (insane๐Ÿคฏ) SOTA in zero-shot layout-to-image generation. Demo available!

๐Ÿ˜ŽReview https://bit.ly/3J0rnHw
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.07093.pdf
๐Ÿ˜ŽCode github.com/gligen/GLIGEN
๐Ÿ˜ŽDemo dev.hliu.cc/gligen_mirror2/
๐Ÿ˜ŽProject gligen.github.io/
๐Ÿ”ฅ9๐Ÿพ2โค1โšก1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿงค Handy: Hands "Pipeline" by #Shopify ๐Ÿงค

๐Ÿ‘‰Shopify open-sourced Handy: hand gestures via #metaquest headsets -> into #Blender

๐Ÿ˜ŽReview https://bit.ly/3Wpkpi2
๐Ÿ˜ŽProject github.com/Shopify/handy
๐Ÿ˜ŽDemo diegomacario.github.io/Hands-In-The-Web/public/index.html
๐Ÿ”ฅ11๐Ÿ‘2๐Ÿ‘2๐Ÿคฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ€ NeRF2NeRF: 3D registration on NeRFs ๐Ÿ€

๐Ÿ‘‰A novel 3D registration that operates directly on NeRFs

๐Ÿ˜ŽReview https://bit.ly/3ZRgz4a
๐Ÿ˜ŽPaper arxiv.org/pdf/2211.01600.pdf
๐Ÿ˜ŽCode github.com/nerf2nerf
๐Ÿ˜ŽProject https://nerf2nerf.github.io/
๐Ÿ˜ŽDataset https://drive.google.com/drive/folders/1jNpwAv1T1ntjIHUMJ1wABePA2Z8_nRRQ
๐Ÿ‘9๐Ÿ”ฅ5
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸŽจ RecolorNeRF: #3D Color Editing ๐ŸŽจ

๐Ÿ‘‰INSANE palette-based color editing of NeRF scenes

๐Ÿ˜ŽReview https://bit.ly/3GYjhfR
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.07958.pdf
๐Ÿ˜ŽProject sites.google.com/view/recolornerf
๐Ÿคฏ10๐Ÿ‘4๐Ÿคฃ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ŸžOmniObject3D: Realistic 3D Dataset ๐Ÿž

๐Ÿ‘‰Large-vocabulary #3D dataset for realistic perception, reconstruction & generation

๐Ÿ˜ŽReview https://bit.ly/3HlXyjp
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.07525.pdf
๐Ÿ˜ŽProject omniobject3d.github.io/
๐Ÿ”ฅ9๐Ÿ‘4โค1๐Ÿคฏ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ‘‘ OnePose++: One-Shot Pose ๐Ÿ‘‘

๐Ÿ‘‰Open-source (insane) keypoint-free pose pipeline for #AR

๐Ÿ˜ŽReview https://bit.ly/3kF0BdG
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.07673.pdf
๐Ÿ˜ŽProject zju3dv.github.io/onepose_plus_plus
๐Ÿ˜ŽCode github.com/zju3dv/OnePose_Plus_Plus
๐Ÿ˜ŽDataset zjueducn-my.sharepoint.com/personal/12121064_zju_edu_cn/_layouts/15/onedrive.aspx
๐Ÿคฏ11๐Ÿ‘9โค1๐Ÿ”ฅ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿ„ BTS: Density Fields from Single View ๐Ÿ„

๐Ÿ‘‰Volumetric scene representation from a single image in challenging conditions

๐Ÿ˜ŽReview https://bit.ly/3wjHDvH
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.07668.pdf
๐Ÿ˜ŽProject fwmb.github.io/bts/
๐Ÿ”ฅ7๐Ÿ‘1๐Ÿ˜ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
โšกStyleGAN-T: unlocking Power of GANsโšก

๐Ÿ‘‰#Nvidia unveils StyleGAN-T to regain competitiveness to GANs vs. Diffusive Models

๐Ÿ˜ŽReview https://bit.ly/3HtKxEA
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.09515.pdf
๐Ÿ˜ŽProject sites.google.com/view/stylegan-t
๐Ÿ˜ŽCode github.com/autonomousvision/stylegan-t
๐Ÿ”ฅ9๐Ÿ‘4๐Ÿคฏ4โค1
This media is not supported in your browser
VIEW IN TELEGRAM
๐Ÿช€ NeRF in Time, Space and Appearance ๐Ÿช€

๐Ÿ‘‰From Berkeley k-planes: a white-box model for radiance fields in arbitrary dimensions

๐Ÿ˜ŽReview https://bit.ly/3J8GiiS
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.10241.pdf
๐Ÿ˜ŽProject sarafridov.github.io/K-Planes/
๐Ÿ˜ŽCode github.com/sarafridov/K-Planes
๐Ÿ‘2๐Ÿคฏ1๐Ÿพ1
Media is too big
VIEW IN TELEGRAM
๐Ÿ”ฅ Neural Tracking via Weighted OF ๐Ÿ”ฅ

๐Ÿ‘‰The new SOTA in planar neural tracking is INSANE!

๐Ÿ˜ŽReview https://bit.ly/404gcDs
๐Ÿ˜ŽPaper arxiv.org/pdf/2301.10057.pdf
๐Ÿ˜ŽCode github.com/serycjon/WOFT
๐Ÿ˜ŽProject cmp.felk.cvut.cz/~serycjon/WOFT
๐Ÿคฏ15โค3๐Ÿ‘3๐Ÿ˜ฑ1