This media is not supported in your browser
VIEW IN TELEGRAM
β½ Stable Diffusion in #Blender β½
πRender with SuperPowers: novel scene render via text prompt
πReview https://bit.ly/3s1mEeN
πCode github.com/benrugg/AI-Render
πRender with SuperPowers: novel scene render via text prompt
πReview https://bit.ly/3s1mEeN
πCode github.com/benrugg/AI-Render
π€―8π5β€2
This media is not supported in your browser
VIEW IN TELEGRAM
β½Markerless Body-Object Interactionβ½
πNovel whole-bodies/objects interaction method from multi-view RGB-D data
πReview https://bit.ly/3yO56GY
πData intercap.is.tue.mpg.de/login.php
πProject https://intercap.is.tue.mpg.de
πCode github.com/YinghaoHuang91
πPaper intercap.is.tue.mpg.de/media/upload/main.pdf
πNovel whole-bodies/objects interaction method from multi-view RGB-D data
πReview https://bit.ly/3yO56GY
πData intercap.is.tue.mpg.de/login.php
πProject https://intercap.is.tue.mpg.de
πCode github.com/YinghaoHuang91
πPaper intercap.is.tue.mpg.de/media/upload/main.pdf
π₯6π2πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯ Dressing Avatars by #META π₯
πNovel deep photorealistic appearance method for physically-simulated clothing in #metaverse
πReview https://bit.ly/3yRBW9Y
πPaper arxiv.org/pdf/2206.15470.pdf
πNovel deep photorealistic appearance method for physically-simulated clothing in #metaverse
πReview https://bit.ly/3yRBW9Y
πPaper arxiv.org/pdf/2206.15470.pdf
π€―7π5πΎ2β€1
AI with Papers - Artificial Intelligence & Deep Learning
π·π·OMNI3D: #3D Objects in the Wildπ·π· π#3D detection: 234k images, 3M+ instances & 97 categories ππ’π π‘π₯π’π π‘ππ¬: β
OMNI3D from publicly released dataset β
234k pics, 3M+ annotation with 3D box β
97 categories such as sofa, table, cars β
Fast (450x) and exact algorithmβ¦
This media is not supported in your browser
VIEW IN TELEGRAM
π₯Meta Omni3D: code is out!π₯
πSource Code, models, and data just released by #META !
πReview https://bit.ly/3MIWxD9
πPaper arxiv.org/pdf/2207.10660.pdf
πProject garrickbrazil.com/omni3d/
πCode github.com/facebookresearch/omni3d
πSource Code, models, and data just released by #META !
πReview https://bit.ly/3MIWxD9
πPaper arxiv.org/pdf/2207.10660.pdf
πProject garrickbrazil.com/omni3d/
πCode github.com/facebookresearch/omni3d
π₯14π2π1
This media is not supported in your browser
VIEW IN TELEGRAM
πͺ Parallel NeRF for 6-DoF pose πͺ
π#Nvidia unveils a parallel NeRF for 6-DoF target pose estimation
πReview https://bit.ly/3guWWwA
πPaper arxiv.org/pdf/2210.10108.pdf
πProject https://pnerfp.github.io/
π#Nvidia unveils a parallel NeRF for 6-DoF target pose estimation
πReview https://bit.ly/3guWWwA
πPaper arxiv.org/pdf/2210.10108.pdf
πProject https://pnerfp.github.io/
π8π₯3
This media is not supported in your browser
VIEW IN TELEGRAM
π¦LaMAR: Localization/Mapping for #ARπ¦
πA new benchmark for #AR in large and unconstrained scenes
πReview https://bit.ly/3DjlnWU
πPaper lamar.ethz.ch/files/LaMAR.pdf
πProject https://lamar.ethz.ch/
πCode github.com/microsoft/lamar-benchmark
πA new benchmark for #AR in large and unconstrained scenes
πReview https://bit.ly/3DjlnWU
πPaper lamar.ethz.ch/files/LaMAR.pdf
πProject https://lamar.ethz.ch/
πCode github.com/microsoft/lamar-benchmark
π7π₯4π―4
This media is not supported in your browser
VIEW IN TELEGRAM
π₯New SOTA in Panoptic Segmentationπ₯
π#Google (with Hintonπ€―) unveils Pix2Seq-D: novel generalist framework for panoptic segmentation
πReview https://bit.ly/3DmpbGM
πPaper arxiv.org/pdf/2210.06366.pdf
π#Google (with Hintonπ€―) unveils Pix2Seq-D: novel generalist framework for panoptic segmentation
πReview https://bit.ly/3DmpbGM
πPaper arxiv.org/pdf/2210.06366.pdf
π₯9π5π€―3
This media is not supported in your browser
VIEW IN TELEGRAM
π¨ UniColor: Unified Colorization π¨
πThe first unified framework for colorization via stroke, exemplar, text, and a mix of them
πReview https://bit.ly/3gESR9y
πPaper arxiv.org/pdf/2209.11223.pdf
πProject luckyhzt.github.io/unicolor
πCode (SOON)
πThe first unified framework for colorization via stroke, exemplar, text, and a mix of them
πReview https://bit.ly/3gESR9y
πPaper arxiv.org/pdf/2209.11223.pdf
πProject luckyhzt.github.io/unicolor
πCode (SOON)
π€―18π₯6π1
This media is not supported in your browser
VIEW IN TELEGRAM
π€― Full-Body from head/hand signals π€―
π#Meta unveils AvatarPoser: first full-body pose method via userβs head/hands
πReview https://bit.ly/3gESR9y
πPaper arxiv.org/pdf/2207.13784.pdf
πCode github.com/eth-siplab/AvatarPoser
π#Meta unveils AvatarPoser: first full-body pose method via userβs head/hands
πReview https://bit.ly/3gESR9y
πPaper arxiv.org/pdf/2207.13784.pdf
πCode github.com/eth-siplab/AvatarPoser
π9π3β€1
This media is not supported in your browser
VIEW IN TELEGRAM
π€JRBD: Egocentric Perception of Humansπ€
πStanford -> JRDB-Pose: Dataset with 600,000+ body pose annotations!
πReview https://bit.ly/3gEZBE4
πPaper arxiv.org/pdf/1910.11792.pdf
πProject jrdb.erc.monash.edu/
πStanford -> JRDB-Pose: Dataset with 600,000+ body pose annotations!
πReview https://bit.ly/3gEZBE4
πPaper arxiv.org/pdf/1910.11792.pdf
πProject jrdb.erc.monash.edu/
π8π―4
This media is not supported in your browser
VIEW IN TELEGRAM
βοΈSOTA Action Detector @90+ FPS!βοΈ
πYOWO-plus: real-time method for spatio-temporal action detection. YOWO-Nano the fastest!
πReview https://bit.ly/3TUdhcI
πPaper arxiv.org/pdf/2210.11219.pdf
πCode github.com/yjh0410/PyTorch_YOWO
πYOWO-plus: real-time method for spatio-temporal action detection. YOWO-Nano the fastest!
πReview https://bit.ly/3TUdhcI
πPaper arxiv.org/pdf/2210.11219.pdf
πCode github.com/yjh0410/PyTorch_YOWO
π13π₯°2
This media is not supported in your browser
VIEW IN TELEGRAM
ποΈποΈAutoregressive NeRF-AvatarποΈποΈ
πAutoAvatar by #Meta: autoregressive method for modeling dynamically deforming human bodies from raw scans
πReview https://bit.ly/3W0oTgo
πPaper arxiv.org/pdf/2203.13817.pdf
πProject zqbai-jeremy.github.io/autoavatar
πCode github.com/facebookresearch/AutoAvatar
πAutoAvatar by #Meta: autoregressive method for modeling dynamically deforming human bodies from raw scans
πReview https://bit.ly/3W0oTgo
πPaper arxiv.org/pdf/2203.13817.pdf
πProject zqbai-jeremy.github.io/autoavatar
πCode github.com/facebookresearch/AutoAvatar
π11π₯2πΎ1
This media is not supported in your browser
VIEW IN TELEGRAM
π―Modeling the Human Pose Manifoldsπ―
π#Meta Pose-NDF: continuous model for plausible human poses based on neural distance fields
πReview https://bit.ly/3f6X59o
πPaper arxiv.org/pdf/2207.13807.pdf
πProject virtualhumans.mpi-inf.mpg.de/posendf
πCode github.com/garvita-tiwari/PoseNDF
π#Meta Pose-NDF: continuous model for plausible human poses based on neural distance fields
πReview https://bit.ly/3f6X59o
πPaper arxiv.org/pdf/2207.13807.pdf
πProject virtualhumans.mpi-inf.mpg.de/posendf
πCode github.com/garvita-tiwari/PoseNDF
β€6π€―4
This media is not supported in your browser
VIEW IN TELEGRAM
π Gesture Recognition in 80's π
πThe #Casio AT-550 was offering the edge gesture recognition in 1984!
πReview https://bit.ly/3fcPia6
πClip: youtube.com/watch?v=piFaJmYpQfQ
πThe #Casio AT-550 was offering the edge gesture recognition in 1984!
πReview https://bit.ly/3fcPia6
πClip: youtube.com/watch?v=piFaJmYpQfQ
π€―15π₯°6π₯2
This media is not supported in your browser
VIEW IN TELEGRAM
πΈMUSIKA! Neural β-audio generationπΈ
πNovel neural music generation system on single consumer GPU!
πListen: https://bit.ly/3W80p4U
πPaper arxiv.org/pdf/2208.08706.pdf
πCode github.com/marcoppasini/musika
πNovel neural music generation system on single consumer GPU!
πListen: https://bit.ly/3W80p4U
πPaper arxiv.org/pdf/2208.08706.pdf
πCode github.com/marcoppasini/musika
π€―8
This media is not supported in your browser
VIEW IN TELEGRAM
π¨οΈMulti NeRF-supervised Depth-Poseπ¨οΈ
πNeRF-supervised disentanglement of depth/camera pose from large-scale clips
πReview https://bit.ly/3gS4Z7e
πPaper arxiv.org/pdf/2210.07181.pdf
πProject oasisyang.github.io/self-mpinerf
πNeRF-supervised disentanglement of depth/camera pose from large-scale clips
πReview https://bit.ly/3gS4Z7e
πPaper arxiv.org/pdf/2210.07181.pdf
πProject oasisyang.github.io/self-mpinerf
π±4
This media is not supported in your browser
VIEW IN TELEGRAM
π§ PlanT: Driving Plan w/ Transformer π§
πPlanT: planning via transformer. Imitation learning with compact object-level representation
πReview https://bit.ly/3Ni2MxN
πProject www.katrinrenz.de/plant/
πPaper arxiv.org/pdf/2210.14222.pdf
πCode github.com/autonomousvision/plant
πPlanT: planning via transformer. Imitation learning with compact object-level representation
πReview https://bit.ly/3Ni2MxN
πProject www.katrinrenz.de/plant/
πPaper arxiv.org/pdf/2210.14222.pdf
πCode github.com/autonomousvision/plant
π₯6π2
This media is not supported in your browser
VIEW IN TELEGRAM
π₯Network -> C++ Converter. Pure Fire!π₯
πFully open source #Python framework to convert Neural Nets into C++. Lightning-fast inferenceπ₯
πReview https://bit.ly/3gSyqWI
πCode github.com/facebookincubator/AITemplate
πFully open source #Python framework to convert Neural Nets into C++. Lightning-fast inferenceπ₯
πReview https://bit.ly/3gSyqWI
πCode github.com/facebookincubator/AITemplate
β€21π€―12π3
This media is not supported in your browser
VIEW IN TELEGRAM
π₯TAVA for photo-realistic Avatarsπ₯
π#META unveils a novel approach for Template-free Animatable Volumetric Avatars. #Metaverse ready.
πReview https://bit.ly/3DPDEvm
πPaper arxiv.org/pdf/2206.08929.pdf
πProject www.liruilong.cn/projects/tava/
πCode github.com/facebookresearch/tava
π#META unveils a novel approach for Template-free Animatable Volumetric Avatars. #Metaverse ready.
πReview https://bit.ly/3DPDEvm
πPaper arxiv.org/pdf/2206.08929.pdf
πProject www.liruilong.cn/projects/tava/
πCode github.com/facebookresearch/tava
π₯°8π1
This media is not supported in your browser
VIEW IN TELEGRAM
π DANNCE: animal keypoints tracking π
πDANNCE: anatomical #3D tracking across species and behaviors
πReview https://bit.ly/3Nrx0P3
πCode https://github.com/spoonsso/dannce
πDANNCE: anatomical #3D tracking across species and behaviors
πReview https://bit.ly/3Nrx0P3
πCode https://github.com/spoonsso/dannce
π₯9π6