This media is not supported in your browser
VIEW IN TELEGRAM
π eDiff-I: Generative AI by #Nvidia π
πeDiff-I: generative AI for text-to-image with instant style transfer & "paint-with-words"
πReview https://bit.ly/3UEESzk
πProject deepimagination.cc/eDiffi
πPaper arxiv.org/pdf/2211.01324.pdf
πeDiff-I: generative AI for text-to-image with instant style transfer & "paint-with-words"
πReview https://bit.ly/3UEESzk
πProject deepimagination.cc/eDiffi
πPaper arxiv.org/pdf/2211.01324.pdf
π€―14β€3π3π₯2π€©1
This media is not supported in your browser
VIEW IN TELEGRAM
βΎ The Universal Image Segmentation βΎ
πOneFormer is the universal framework that unifies: semantic, instance & panoptic π€―
πReview https://bit.ly/3g4OAfD
πProject praeclarumjj3.github.io/oneformer
πPaper arxiv.org/pdf/2211.06220.pdf
πCode github.com/SHI-Labs/OneFormer
πOneFormer is the universal framework that unifies: semantic, instance & panoptic π€―
πReview https://bit.ly/3g4OAfD
πProject praeclarumjj3.github.io/oneformer
πPaper arxiv.org/pdf/2211.06220.pdf
πCode github.com/SHI-Labs/OneFormer
π±6π5
This media is not supported in your browser
VIEW IN TELEGRAM
π₯ ROVIS: Robust Online VIS π₯
πROVIS is a novel method for robust online VIS that exhibits impressive accuracy on long clips
πReview https://bit.ly/3UMugyv
πProject zitongzhan.github.io/rovis_page/
πPaper arxiv.org/pdf/2211.09108.pdf
πROVIS is a novel method for robust online VIS that exhibits impressive accuracy on long clips
πReview https://bit.ly/3UMugyv
πProject zitongzhan.github.io/rovis_page/
πPaper arxiv.org/pdf/2211.09108.pdf
β€10π2π€―1
This media is not supported in your browser
VIEW IN TELEGRAM
π FathomNet: #AI in the Oceans π
πOpen-source image dataset for AI about oceans and its inhabitants
πReview https://bit.ly/3GsW3jh
πProject fathomnet.org/fathomnet/#/
πPaper www.nature.com/articles/s41598-022-19939-2
πOpen-source image dataset for AI about oceans and its inhabitants
πReview https://bit.ly/3GsW3jh
πProject fathomnet.org/fathomnet/#/
πPaper www.nature.com/articles/s41598-022-19939-2
β€9π₯°4π2β‘1
This media is not supported in your browser
VIEW IN TELEGRAM
π 3DiM: Diffusion Model by Google π
π3DiM: diffusion model for 3D novel view synthesis from as few as a single image
πReview bit.ly/3UTJFgA
πProject 3d-diffusion.github.io
πPaper arxiv.org/pdf/2210.04628.pdf
π3DiM: diffusion model for 3D novel view synthesis from as few as a single image
πReview bit.ly/3UTJFgA
πProject 3d-diffusion.github.io
πPaper arxiv.org/pdf/2210.04628.pdf
π8π2β‘1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯#StableDiffusion Dataset is out! π₯
πDIFFUSIONDB: first large-scale text-to-image dataset: 14 MILLION images with Stable Diffusion!
πReview https://bit.ly/3V9CpNh
πProject poloclub.github.io/diffusiondb
πPaper arxiv.org/pdf/2210.14896.pdf
πRepo github.com/poloclub/diffusiondb
πDIFFUSIONDB: first large-scale text-to-image dataset: 14 MILLION images with Stable Diffusion!
πReview https://bit.ly/3V9CpNh
πProject poloclub.github.io/diffusiondb
πPaper arxiv.org/pdf/2210.14896.pdf
πRepo github.com/poloclub/diffusiondb
π€―11π₯6π4β€1π©1πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
πͺThe new SOTA in Text-to-3D is out!πͺ
π#Nvidia unveils Magic3D: generative #AI to create #3D textured mesh from text prompts
πReview https://bit.ly/3Vb6jAO
πProject deepimagination.cc/Magic3D
πPaper arxiv.org/pdf/2211.10440.pdf
π#Nvidia unveils Magic3D: generative #AI to create #3D textured mesh from text prompts
πReview https://bit.ly/3Vb6jAO
πProject deepimagination.cc/Magic3D
πPaper arxiv.org/pdf/2211.10440.pdf
π€―5π3π₯3β€1β‘1
This media is not supported in your browser
VIEW IN TELEGRAM
πΈFlying-Drones Additive ManufacturingπΈ
πA novel aerial additive manufacturing (Aerial-AM) system via Drones
πReview https://bit.ly/3XoLZOu
πPaper www.nature.com/articles/s41586-022-04988-4
πA novel aerial additive manufacturing (Aerial-AM) system via Drones
πReview https://bit.ly/3XoLZOu
πPaper www.nature.com/articles/s41586-022-04988-4
π6π€―2π±2
This media is not supported in your browser
VIEW IN TELEGRAM
π₯Perfect Human Annotation by Google!π₯
πTAP-Vid dataset: accurate human annotations + synthetic videos with PERFECT ground-truth
πReview https://bit.ly/3i1KRzZ
πCode github.com/deepmind/tapnet
πPaper arxiv.org/pdf/2211.03726.pdf
πTAP-Vid dataset: accurate human annotations + synthetic videos with PERFECT ground-truth
πReview https://bit.ly/3i1KRzZ
πCode github.com/deepmind/tapnet
πPaper arxiv.org/pdf/2211.03726.pdf
π₯6π2β‘1π1
This media is not supported in your browser
VIEW IN TELEGRAM
π΄VideoINR: Neural Video Super-Resolutionπ΄
πVideoINR: the new SOTA in Continuous Space-Time Super-Resolution is out!
πReview https://bit.ly/3gpeudY
πPaper arxiv.org/pdf/2206.04647.pdf
πProject zeyuan-chen.com/VideoINR
πCode github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution
πVideoINR: the new SOTA in Continuous Space-Time Super-Resolution is out!
πReview https://bit.ly/3gpeudY
πPaper arxiv.org/pdf/2206.04647.pdf
πProject zeyuan-chen.com/VideoINR
πCode github.com/Picsart-AI-Research/VideoINR-Continuous-Space-Time-Super-Resolution
π€―6π1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯π₯MagicVideo: Text-To-Video #AIπ₯π₯
πMagicVideo: novel efficient text-to-video AI based on latent diffusion models
πReview https://bit.ly/3UX5YCd
πPaper arxiv.org/pdf/2211.11018.pdf
πProject magicvideo.github.io/
πMagicVideo: novel efficient text-to-video AI based on latent diffusion models
πReview https://bit.ly/3UX5YCd
πPaper arxiv.org/pdf/2211.11018.pdf
πProject magicvideo.github.io/
π±8π2π©1
This media is not supported in your browser
VIEW IN TELEGRAM
π§ββοΈ Generative Neural Texture for Avatars π§ββοΈ
πNovel #3D GAN for (the most, ever) detailed facial avatars from unstructured 2D images
πReview https://bit.ly/3EvF0dS
πProject mrtornado24.github.io/Next3D/
πPaper arxiv.org/pdf/2211.11208.pdf
πCode github.com/MrTornado24/Next3D
πNovel #3D GAN for (the most, ever) detailed facial avatars from unstructured 2D images
πReview https://bit.ly/3EvF0dS
πProject mrtornado24.github.io/Next3D/
πPaper arxiv.org/pdf/2211.11208.pdf
πCode github.com/MrTornado24/Next3D
π₯6π±4π2
π₯π₯ "There can be only one" π₯π₯
π#Catfighting from the #AI community π
πReview https://bit.ly/3Ax5I4n
π#Catfighting from the #AI community π
πReview https://bit.ly/3Ax5I4n
π€£7π5πΎ2
This media is not supported in your browser
VIEW IN TELEGRAM
ποΈ Neural Semantic Image Synthesis ποΈ
πAdobe unveils SceneComposer: text to 2D semantic canvas with precise shapes
πReview https://bit.ly/3EtDyIL
πProject zengyu.me/scenec
πPaper arxiv.org/pdf/2211.11742.pdf
πCode github.com/zengxianyu/scenec
πAdobe unveils SceneComposer: text to 2D semantic canvas with precise shapes
πReview https://bit.ly/3EtDyIL
πProject zengyu.me/scenec
πPaper arxiv.org/pdf/2211.11742.pdf
πCode github.com/zengxianyu/scenec
π€―10β€4β‘1π1
This media is not supported in your browser
VIEW IN TELEGRAM
πΉ Perceptual NeRF-Inpainting πΉ
πA novel complete process for #3D scene manipulation powered by NeRF
πReview https://bit.ly/3Vn0EaT
πPaper arxiv.org/pdf/2211.12254.pdf
πProject spinnerf3d.github.io
πA novel complete process for #3D scene manipulation powered by NeRF
πReview https://bit.ly/3Vn0EaT
πPaper arxiv.org/pdf/2211.12254.pdf
πProject spinnerf3d.github.io
π5π₯3πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯ Stable Diffusion 2.0 is out! π₯
πThe open-source of #StableDiffusion V2 just released. Magic π€―
πReview https://bit.ly/3XwGInO
πCode github.com/Stability-AI/stablediffusion
πBlog stability.ai/blog/stable-diffusion-v2-release
πThe open-source of #StableDiffusion V2 just released. Magic π€―
πReview https://bit.ly/3XwGInO
πCode github.com/Stability-AI/stablediffusion
πBlog stability.ai/blog/stable-diffusion-v2-release
π€―17π8πΎ4β‘3π±3π1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯MineDojo: Agents at Internet-Scaleπ₯
πThe #neurips2022 Outstanding Paper Award winner is out. By #Nvidia et al.
πReview https://bit.ly/3F0RPhN
πProject https://minedojo.org/
πPaper arxiv.org/pdf/2206.08853.pdf
πCode github.com/MineDojo/MineDojo
πThe #neurips2022 Outstanding Paper Award winner is out. By #Nvidia et al.
πReview https://bit.ly/3F0RPhN
πProject https://minedojo.org/
πPaper arxiv.org/pdf/2206.08853.pdf
πCode github.com/MineDojo/MineDojo
π₯10π€©1
AI with Papers - Artificial Intelligence & Deep Learning
π· Pix2Seq: object detection by #Google π· πA novel framework to perform object detection as a language modeling task ππ’π π‘π₯π’π π‘ππ¬: β
Obj. detection as a lang-modeling task β
BBs/labels -> seq. of discrete token β
Encoder-decoder (one token at a time) β
Code underβ¦
This media is not supported in your browser
VIEW IN TELEGRAM
β‘4π₯°2π1π±1
This media is not supported in your browser
VIEW IN TELEGRAM
π« Tracking in Motion-Blurred Clips π«
πRobust line segment detector in motion-blurred clips -> #SLAM / #3D.
πReview https://bit.ly/3F2wHrb
πPaper arxiv.org/pdf/2211.07365.pdf
πProject levenberg.github.io/FE-LSD/
πCode github.com/lh9171338/FE-LSD
πRobust line segment detector in motion-blurred clips -> #SLAM / #3D.
πReview https://bit.ly/3F2wHrb
πPaper arxiv.org/pdf/2211.07365.pdf
πProject levenberg.github.io/FE-LSD/
πCode github.com/lh9171338/FE-LSD
π€―5π2π₯2β‘1
This media is not supported in your browser
VIEW IN TELEGRAM
πEDGE: Diffusive Dancers Generatorπ
πNew SOTA in editable human-dancer generation according to the input music
πReview https://bit.ly/3u2egfY
πPaper arxiv.org/pdf/2211.10658.pdf
πProject edge-dance.github.io/
πNew SOTA in editable human-dancer generation according to the input music
πReview https://bit.ly/3u2egfY
πPaper arxiv.org/pdf/2211.10658.pdf
πProject edge-dance.github.io/
β€8π€©2π€―1