This media is not supported in your browser
VIEW IN TELEGRAM
๐ข #AI Advanced Math Reasoning ๐ข
๐#Meta unveils HTPS: SOTA transformer-based theorem prover.
๐Review https://bit.ly/3CoUsrP
๐Paper arxiv.org/pdf/2205.11491.pdf
๐Blog ai.facebook.com/blog/ai-math-theorem-proving
๐#Meta unveils HTPS: SOTA transformer-based theorem prover.
๐Review https://bit.ly/3CoUsrP
๐Paper arxiv.org/pdf/2205.11491.pdf
๐Blog ai.facebook.com/blog/ai-math-theorem-proving
๐คฏ16๐ฑ3๐1๐ฅฐ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ฅ YOLOv5 Segmentation in OpenCV ๐ฅ
๐#OpenCV recently added the support for YOLOv5 instance segmentation
๐Review https://bit.ly/3idVNeb
๐Code github.com/ultralytics/yolov5
๐Tutorial learnopencv.com/yolov5-instance-segmentation
๐#OpenCV recently added the support for YOLOv5 instance segmentation
๐Review https://bit.ly/3idVNeb
๐Code github.com/ultralytics/yolov5
๐Tutorial learnopencv.com/yolov5-instance-segmentation
๐ฅ19๐3โค2๐คฏ2๐พ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ Nvidia + ByteDance CV-CUDA ๐
๐CV-CUDA: open-source, GPU-accelerated lib for CV developed jointly by NVIDIA / ByteDance
๐Review https://bit.ly/3GHSaqu
๐Code github.com/CVCUDA/CV-CUDA
๐CV-CUDA: open-source, GPU-accelerated lib for CV developed jointly by NVIDIA / ByteDance
๐Review https://bit.ly/3GHSaqu
๐Code github.com/CVCUDA/CV-CUDA
๐ฅ8๐2๐ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ฅ Source Code of Box2mask is out! ๐ฅ
๐BoxInstSeg is a toolbox for SOTA box-supervised instance segmentation
๐Review https://bit.ly/3QryBGf
๐Code github.com/LiWentomng/BoxInstSeg
๐BoxInstSeg is a toolbox for SOTA box-supervised instance segmentation
๐Review https://bit.ly/3QryBGf
๐Code github.com/LiWentomng/BoxInstSeg
๐ฅ18๐5โค1๐ฑ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ฃ๏ธ MemFace: Generative Talking Face ๐ฃ๏ธ
๐#Microsoft (+SJTU) unveils MemFace: the new SOTA in talking faces generation
๐Review https://bit.ly/3k8TjhZ
๐Paper arxiv.org/pdf/2212.05005v2.pdf
๐Project memoryface.github.io/
๐#Microsoft (+SJTU) unveils MemFace: the new SOTA in talking faces generation
๐Review https://bit.ly/3k8TjhZ
๐Paper arxiv.org/pdf/2212.05005v2.pdf
๐Project memoryface.github.io/
๐คฏ12๐คฉ3๐1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ช AgileAvatar: HQ stylized 3D #Avatar ๐ช
๐#ByteDance unveils a novel self-supervised framework for #3D avatars
๐Review https://bit.ly/3kaOAw6
๐Project ssangx.github.io/projects/agileavatar
๐Paper ssangx.github.io/pubs/2022-SIGGRAPHAsia-AgileAvatar.pdf
๐#ByteDance unveils a novel self-supervised framework for #3D avatars
๐Review https://bit.ly/3kaOAw6
๐Project ssangx.github.io/projects/agileavatar
๐Paper ssangx.github.io/pubs/2022-SIGGRAPHAsia-AgileAvatar.pdf
๐9โค3
๐ฅ #Nvidia GC ViT Large -> updated! ๐ฅ
๐The new SOTA (with large margin) across image classification, detection & semantic segmentation!
๐Review https://bit.ly/3W4ChyF
๐Code github.com/NVlabs/GCViT
๐Paper arxiv.org/pdf/2206.09959.pdf
๐The new SOTA (with large margin) across image classification, detection & semantic segmentation!
๐Review https://bit.ly/3W4ChyF
๐Code github.com/NVlabs/GCViT
๐Paper arxiv.org/pdf/2206.09959.pdf
๐ฅ6
This media is not supported in your browser
VIEW IN TELEGRAM
๐๏ธ VecGAN: DETAILED Face Manipulation ๐๏ธ
๐ VecGAN: SOTA I2I for facial editing with interpretable latent directions
๐Review https://bit.ly/3GGNUpZ
๐Project yusufdalva.github.io/vecgan/
๐Code github.com/yusufdalva/VecGAN
๐Paper arxiv.org/pdf/2207.03411.pdf
๐ VecGAN: SOTA I2I for facial editing with interpretable latent directions
๐Review https://bit.ly/3GGNUpZ
๐Project yusufdalva.github.io/vecgan/
๐Code github.com/yusufdalva/VecGAN
๐Paper arxiv.org/pdf/2207.03411.pdf
๐คฏ6
๐ง HOTCOLD: Thermal Adv-Fashion ๐ง
๐A novel physical attack for IR cams via wearable temperature-sensitive patches
๐Review https://bit.ly/3k8mt0B
๐Paper arxiv.org/pdf/2212.05709.pdf
๐Code github.com/weihui1308/HOTCOLDBlock
๐A novel physical attack for IR cams via wearable temperature-sensitive patches
๐Review https://bit.ly/3k8mt0B
๐Paper arxiv.org/pdf/2212.05709.pdf
๐Code github.com/weihui1308/HOTCOLDBlock
๐คฉ5
This media is not supported in your browser
VIEW IN TELEGRAM
๐ New Task in #AI: Domain Expansion ๐
๐#Adobe on augmenting the space a model can generate, without overriding its original behavior
๐Review https://bit.ly/3ZCtwPA
๐Paper arxiv.org/pdf/2301.05225.pdf
๐Project yotamnitzan.github.io/domain-expansion
๐Code github.com/adobe-research/domain-expansion
๐#Adobe on augmenting the space a model can generate, without overriding its original behavior
๐Review https://bit.ly/3ZCtwPA
๐Paper arxiv.org/pdf/2301.05225.pdf
๐Project yotamnitzan.github.io/domain-expansion
๐Code github.com/adobe-research/domain-expansion
๐2๐ฑ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐ MMEditing: SOTA toolbox for #AI ๐
๐An open-source image/video editing toolbox based on #PyTorch
๐Review https://bit.ly/3k4cmK8
๐Project github.com/open-mmlab/mmediting
๐An open-source image/video editing toolbox based on #PyTorch
๐Review https://bit.ly/3k4cmK8
๐Project github.com/open-mmlab/mmediting
๐ฅ12๐4
๐ถ Dense Pose from WiFi ๐ถ
๐AI able to map phase/amplitude of WiFi signals for human sensing application
๐Review https://bit.ly/3QDeFQC
๐Paper arxiv.org/pdf/2301.00250.pdf
๐AI able to map phase/amplitude of WiFi signals for human sensing application
๐Review https://bit.ly/3QDeFQC
๐Paper arxiv.org/pdf/2301.00250.pdf
๐คฏ33๐ฅ5๐2๐ฑ2
This media is not supported in your browser
VIEW IN TELEGRAM
๐ต๏ธ Instant-NeRF Artists Gallery ๐ต๏ธ
๐A gallery of beautiful scenes powered by the #NVIDIA Instant-NeRF
๐Review https://bit.ly/3XxV9au
๐Gallery www.nvidia.com/en-us/research/ai-art-gallery/instant-nerf
๐A gallery of beautiful scenes powered by the #NVIDIA Instant-NeRF
๐Review https://bit.ly/3XxV9au
๐Gallery www.nvidia.com/en-us/research/ai-art-gallery/instant-nerf
๐ฅ7๐2๐ฅฐ2โค1
๐ชท Saliency Detection by/for Impaired ๐ชท
๐A novel dataset using images taken by visually impaired people. Suitable for (big object/text) saliency detectors
๐Paper arxiv.org/pdf/2301.05323.pdf
๐Data vizwiz.org/tasks-and-datasets/salient-object-detection
๐Code vizwiz.org/wp-content/uploads/2023/01/sod_mask_example.txt
๐A novel dataset using images taken by visually impaired people. Suitable for (big object/text) saliency detectors
๐Paper arxiv.org/pdf/2301.05323.pdf
๐Data vizwiz.org/tasks-and-datasets/salient-object-detection
๐Code vizwiz.org/wp-content/uploads/2023/01/sod_mask_example.txt
๐ฅ10
๐งช YOLOv6 v3.0 is out! ๐งช
๐Meituan open-sourced YOLOv6 v3.0: many novel enhancements on architecture & training scheme. New SOTA on COCO!
๐Review https://bit.ly/3wbj7wC
๐Paper arxiv.org/pdf/2301.05586.pdf
๐Code github.com/meituan/YOLOv6
๐Meituan open-sourced YOLOv6 v3.0: many novel enhancements on architecture & training scheme. New SOTA on COCO!
๐Review https://bit.ly/3wbj7wC
๐Paper arxiv.org/pdf/2301.05586.pdf
๐Code github.com/meituan/YOLOv6
๐ฅ7๐คฃ7๐พ3
This media is not supported in your browser
VIEW IN TELEGRAM
๐ฅซ Plug 'n' play self-checkout ๐ฅซ
๐#Google's new shelf-checking #AI: recognizing billions of products, even purchased/moved
๐Review https://bit.ly/3J58hQe
๐News https://cloud.google.com/blog/transform/nrf-2023-google-cloud-big-show-big-moment-hybrid-retail
๐#Google's new shelf-checking #AI: recognizing billions of products, even purchased/moved
๐Review https://bit.ly/3J58hQe
๐News https://cloud.google.com/blog/transform/nrf-2023-google-cloud-big-show-big-moment-hybrid-retail
๐คฏ8๐7
This media is not supported in your browser
VIEW IN TELEGRAM
๐ GLIGEN: Grounded T2I Diffusion ๐
๐New (insane๐คฏ) SOTA in zero-shot layout-to-image generation. Demo available!
๐Review https://bit.ly/3J0rnHw
๐Paper arxiv.org/pdf/2301.07093.pdf
๐Code github.com/gligen/GLIGEN
๐Demo dev.hliu.cc/gligen_mirror2/
๐Project gligen.github.io/
๐New (insane๐คฏ) SOTA in zero-shot layout-to-image generation. Demo available!
๐Review https://bit.ly/3J0rnHw
๐Paper arxiv.org/pdf/2301.07093.pdf
๐Code github.com/gligen/GLIGEN
๐Demo dev.hliu.cc/gligen_mirror2/
๐Project gligen.github.io/
๐ฅ9๐พ2โค1โก1
This media is not supported in your browser
VIEW IN TELEGRAM
๐งค Handy: Hands "Pipeline" by #Shopify ๐งค
๐Shopify open-sourced Handy: hand gestures via #metaquest headsets -> into #Blender
๐Review https://bit.ly/3Wpkpi2
๐Project github.com/Shopify/handy
๐Demo diegomacario.github.io/Hands-In-The-Web/public/index.html
๐Shopify open-sourced Handy: hand gestures via #metaquest headsets -> into #Blender
๐Review https://bit.ly/3Wpkpi2
๐Project github.com/Shopify/handy
๐Demo diegomacario.github.io/Hands-In-The-Web/public/index.html
๐ฅ11๐2๐2๐คฉ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐ NeRF2NeRF: 3D registration on NeRFs ๐
๐A novel 3D registration that operates directly on NeRFs
๐Review https://bit.ly/3ZRgz4a
๐Paper arxiv.org/pdf/2211.01600.pdf
๐Code github.com/nerf2nerf
๐Project https://nerf2nerf.github.io/
๐Dataset https://drive.google.com/drive/folders/1jNpwAv1T1ntjIHUMJ1wABePA2Z8_nRRQ
๐A novel 3D registration that operates directly on NeRFs
๐Review https://bit.ly/3ZRgz4a
๐Paper arxiv.org/pdf/2211.01600.pdf
๐Code github.com/nerf2nerf
๐Project https://nerf2nerf.github.io/
๐Dataset https://drive.google.com/drive/folders/1jNpwAv1T1ntjIHUMJ1wABePA2Z8_nRRQ
๐9๐ฅ5
This media is not supported in your browser
VIEW IN TELEGRAM
๐จ RecolorNeRF: #3D Color Editing ๐จ
๐INSANE palette-based color editing of NeRF scenes
๐Review https://bit.ly/3GYjhfR
๐Paper arxiv.org/pdf/2301.07958.pdf
๐Project sites.google.com/view/recolornerf
๐INSANE palette-based color editing of NeRF scenes
๐Review https://bit.ly/3GYjhfR
๐Paper arxiv.org/pdf/2301.07958.pdf
๐Project sites.google.com/view/recolornerf
๐คฏ10๐4๐คฃ1
This media is not supported in your browser
VIEW IN TELEGRAM
๐OmniObject3D: Realistic 3D Dataset ๐
๐Large-vocabulary #3D dataset for realistic perception, reconstruction & generation
๐Review https://bit.ly/3HlXyjp
๐Paper arxiv.org/pdf/2301.07525.pdf
๐Project omniobject3d.github.io/
๐Large-vocabulary #3D dataset for realistic perception, reconstruction & generation
๐Review https://bit.ly/3HlXyjp
๐Paper arxiv.org/pdf/2301.07525.pdf
๐Project omniobject3d.github.io/
๐ฅ9๐4โค1๐คฏ1