π SplineCam: Neural Decision Boundary π
π#META -> SplineCam: a step towards neural visualization / interpretability
πReview https://bit.ly/3mgoOaH
πPaper arxiv.org/pdf/2302.12828.pdf
πProject imtiazhumayun.github.io/splinecam
πCode github.com/AhmedImtiazPrio/SplineCAM
π#META -> SplineCam: a step towards neural visualization / interpretability
πReview https://bit.ly/3mgoOaH
πPaper arxiv.org/pdf/2302.12828.pdf
πProject imtiazhumayun.github.io/splinecam
πCode github.com/AhmedImtiazPrio/SplineCAM
π€―8π3
This media is not supported in your browser
VIEW IN TELEGRAM
π ControNet: Conditional Control of Diffusion π
πControlling Stable Diffusion via conditional inputs like edges, segmentation, keypoints, etc. Extra: a super-nice tutorial.
πReview https://bit.ly/3YgjrWt
πPaper arxiv.org/pdf/2302.05543.pdf
πCode github.com/lllyasviel/ControlNet
πTutorial https://github.com/Mikubill/sd-webui-controlnet/discussions/204
πControlling Stable Diffusion via conditional inputs like edges, segmentation, keypoints, etc. Extra: a super-nice tutorial.
πReview https://bit.ly/3YgjrWt
πPaper arxiv.org/pdf/2302.05543.pdf
πCode github.com/lllyasviel/ControlNet
πTutorial https://github.com/Mikubill/sd-webui-controlnet/discussions/204
π€―15π8π₯3β€1
This media is not supported in your browser
VIEW IN TELEGRAM
πΈ TAU: video traffic analytics via UAVs πΈ
π Prince Sultan University unveils TAU: AI-integrated video analytics framework from UAVs' POV
πReview https://bit.ly/3EQIh8F
πPaper arxiv.org/pdf/2303.00337.pdf
πProject github.com/bilel-bj/TAU
π Prince Sultan University unveils TAU: AI-integrated video analytics framework from UAVs' POV
πReview https://bit.ly/3EQIh8F
πPaper arxiv.org/pdf/2303.00337.pdf
πProject github.com/bilel-bj/TAU
π₯10π3π₯°1πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
π©» Independent Tokens for 3D Human π©»
πTencent open-sourcing a novel method to estimate #3D human pose and shape from monocular videos
πReview https://bit.ly/3Zz0uiH
πPaper arxiv.org/pdf/2303.00298.pdf
πCode github.com/yangsenius/INT_HMR_Model
πProject yangsenius.github.io/INT_HMR_Model/index.html
πTencent open-sourcing a novel method to estimate #3D human pose and shape from monocular videos
πReview https://bit.ly/3Zz0uiH
πPaper arxiv.org/pdf/2303.00298.pdf
πCode github.com/yangsenius/INT_HMR_Model
πProject yangsenius.github.io/INT_HMR_Model/index.html
π₯5π1π’1
This media is not supported in your browser
VIEW IN TELEGRAM
πΈ 3DGP: ImageNet in #3D πΈ
π Snap unveils 3DGP: a novel 3D generator with Generic Priors
πReview https://bit.ly/3KWHUgG
πPaper arxiv.org/pdf/2303.01416.pdf
πProject snap-research.github.io/3dgp/
πCode github.com/snap-research/3dgp
π Snap unveils 3DGP: a novel 3D generator with Generic Priors
πReview https://bit.ly/3KWHUgG
πPaper arxiv.org/pdf/2303.01416.pdf
πProject snap-research.github.io/3dgp/
πCode github.com/snap-research/3dgp
π₯8β‘1π1
Media is too big
VIEW IN TELEGRAM
πΊοΈ S-NeRF: NeRF for Street Views πΊοΈ
πS-NeRF: novel view synthesis of streets & foreground moving vehicles jointly
πReview https://bit.ly/3KZUN9w
πPaper arxiv.org/pdf/2303.00749.pdf
πProject ziyang-xie.github.io/s-nerf/
πCode (soon)
πS-NeRF: novel view synthesis of streets & foreground moving vehicles jointly
πReview https://bit.ly/3KZUN9w
πPaper arxiv.org/pdf/2303.00749.pdf
πProject ziyang-xie.github.io/s-nerf/
πCode (soon)
π9π₯3π€―1
This media is not supported in your browser
VIEW IN TELEGRAM
π§± MobileBrick: #3D object on mobile π§±
π#Apple (+Oxford) exploiting #LEGO bricks to open the most precise #3D dataset ever. Suitable for mobile #AR
πReview https://bit.ly/3ZqbiAh
πPaper arxiv.org/pdf/2303.01932.pdf
πProject code.active.vision/MobileBrick/
πCode github.com/ActiveVisionLab/MobileBrick
π#Apple (+Oxford) exploiting #LEGO bricks to open the most precise #3D dataset ever. Suitable for mobile #AR
πReview https://bit.ly/3ZqbiAh
πPaper arxiv.org/pdf/2303.01932.pdf
πProject code.active.vision/MobileBrick/
πCode github.com/ActiveVisionLab/MobileBrick
π₯6π2π±1
This media is not supported in your browser
VIEW IN TELEGRAM
β οΈ BREAKING: Stability Acquires Init ML β οΈ
π Stability AI (#stablediffusion) announces the acquisition of Clipdrop makers π€―
π More: https://bit.ly/3JhKkVO
π Stability AI (#stablediffusion) announces the acquisition of Clipdrop makers π€―
π More: https://bit.ly/3JhKkVO
π€―7β€2π2π₯°1π1π±1πΎ1
π π‘ DeepSeeColor: Under the Sea in Colors π‘π
π DeepSeeColor: real-time adaptive color correction under the sea
πReview https://bit.ly/3mxGuyP
πPaper arxiv.org/pdf/2303.04025.pdf
πCode warp.whoi.edu/deepseecolor
π DeepSeeColor: real-time adaptive color correction under the sea
πReview https://bit.ly/3mxGuyP
πPaper arxiv.org/pdf/2303.04025.pdf
πCode warp.whoi.edu/deepseecolor
π₯°16π4π2
This media is not supported in your browser
VIEW IN TELEGRAM
π§© X-Avatar: Expressive Human Avatars π§©
πETHZ (+Microsoft) unveils X-Avatar: digital expressive humans for life-like experiences (#AR / #VR)
πReview https://bit.ly/3J6YDLH
πPaper arxiv.org/pdf/2303.04805.pdf
πProject https://skype-line.github.io/projects/X-Avatar/
πCode https://github.com/Skype-line/X-Avatar
πETHZ (+Microsoft) unveils X-Avatar: digital expressive humans for life-like experiences (#AR / #VR)
πReview https://bit.ly/3J6YDLH
πPaper arxiv.org/pdf/2303.04805.pdf
πProject https://skype-line.github.io/projects/X-Avatar/
πCode https://github.com/Skype-line/X-Avatar
π₯4π€―3π1π±1
This media is not supported in your browser
VIEW IN TELEGRAM
π Visual ChatGPT: Talking, Drawing & Editing π
π Microsoft extends ChatGPT to handle visual information
πReview https://bit.ly/3LkSJJD
πPaper arxiv.org/pdf/2303.04671.pdf
πCode github.com/microsoft/visual-chatgpt
π Microsoft extends ChatGPT to handle visual information
πReview https://bit.ly/3LkSJJD
πPaper arxiv.org/pdf/2303.04671.pdf
πCode github.com/microsoft/visual-chatgpt
π€―13π₯8β€7π3π±1
This media is not supported in your browser
VIEW IN TELEGRAM
π’ GigaGAN: ultra-GAN Synthesis π’
π Novel method that far exceeds the previous limits of GAN -> ultra HD images!
πReview https://bit.ly/3ZYnZBX
πPaper arxiv.org/pdf/2303.05511.pdf
πProject mingukkang.github.io/GigaGAN
π Novel method that far exceeds the previous limits of GAN -> ultra HD images!
πReview https://bit.ly/3ZYnZBX
πPaper arxiv.org/pdf/2303.05511.pdf
πProject mingukkang.github.io/GigaGAN
π₯30β€6π€©1
π The baby is born: GPT-4 is out! π
πGPT-4 is the new LLM (accepting image and text inputs, emitting text outputs) with human-level performance on various professional and academic benchmarks
πMore: https://bit.ly/3LntuWL
πGPT-4 is the new LLM (accepting image and text inputs, emitting text outputs) with human-level performance on various professional and academic benchmarks
πMore: https://bit.ly/3LntuWL
π₯40π€―6π±5π©5β€4π1π1πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
πViperGPT: Visual Inference / Reasoningπ
πViperGPT: vision/language -> code to produce results for any query
πReview https://bit.ly/3n6yw01
πPaper arxiv.org/pdf/2303.08128.pdf
πProject viper.cs.columbia.edu/
πCode github.com/cvlab-columbia/viper
πViperGPT: vision/language -> code to produce results for any query
πReview https://bit.ly/3n6yw01
πPaper arxiv.org/pdf/2303.08128.pdf
πProject viper.cs.columbia.edu/
πCode github.com/cvlab-columbia/viper
π€―13π₯6β€1
This media is not supported in your browser
VIEW IN TELEGRAM
π SDFStudio: Unified Surface Reconstruction π
πA unified (and open) framework for neural implicit surface reconstruction
πReview https://bit.ly/3yUvuP2
πProject autonomousvision.github.io/sdfstudio
πCode github.com/autonomousvision/sdfstudio
πDoc github.com/autonomousvision/sdfstudio/blob/master/docs/sdfstudio-methods.md
πA unified (and open) framework for neural implicit surface reconstruction
πReview https://bit.ly/3yUvuP2
πProject autonomousvision.github.io/sdfstudio
πCode github.com/autonomousvision/sdfstudio
πDoc github.com/autonomousvision/sdfstudio/blob/master/docs/sdfstudio-methods.md
π€―5π2π₯2
This media is not supported in your browser
VIEW IN TELEGRAM
π e-book: Understanding Deep Learning π
πFrom MIT Press, a free & fresh book for mastering the Deep Learning & #AI
πDownload https://bit.ly/3JUHMNv
πFrom MIT Press, a free & fresh book for mastering the Deep Learning & #AI
πDownload https://bit.ly/3JUHMNv
β€14π4
This media is not supported in your browser
VIEW IN TELEGRAM
π CC3D: Layout-Conditioned 3D π
πA novel step towards the realistic multi-object scene generation
πReview https://bit.ly/3JXG0v3
πPaper arxiv.org/pdf/2303.12074.pdf
πProject sherwinbahmani.github.io/cc3d
πCode github.com/sherwinbahmani/cc3d
πA novel step towards the realistic multi-object scene generation
πReview https://bit.ly/3JXG0v3
πPaper arxiv.org/pdf/2303.12074.pdf
πProject sherwinbahmani.github.io/cc3d
πCode github.com/sherwinbahmani/cc3d
π₯5β€2π1
This media is not supported in your browser
VIEW IN TELEGRAM
π #3D editing via text instructions π
πA novel method for editing NeRF scenes with text-instructions
πReview https://bit.ly/3K3putM
πPaper arxiv.org/pdf/2303.12789.pdf
πProject instruct-nerf2nerf.github.io
πA novel method for editing NeRF scenes with text-instructions
πReview https://bit.ly/3K3putM
πPaper arxiv.org/pdf/2303.12789.pdf
πProject instruct-nerf2nerf.github.io
π₯11π€―3β€1π1