This media is not supported in your browser
VIEW IN TELEGRAM
🌈 Track Everything Everywhere 🌈
👉#Google unveils OmniMotion: full-length motion tracking for every pixel in every frame of video.
😎Review https://t.ly/Krvw
😎Paper arxiv.org/pdf/2306.05422.pdf
😎Project omnimotion.github.io/
😎Demo omnimotion.github.io/#interactive_demo
😎Code github.com/qianqianwang68/omnimotion
👉#Google unveils OmniMotion: full-length motion tracking for every pixel in every frame of video.
😎Review https://t.ly/Krvw
😎Paper arxiv.org/pdf/2306.05422.pdf
😎Project omnimotion.github.io/
😎Demo omnimotion.github.io/#interactive_demo
😎Code github.com/qianqianwang68/omnimotion
🔥23❤5🤯3🤩1💩1
This media is not supported in your browser
VIEW IN TELEGRAM
👁️ Scene Five: Through Her Eyes 👁️
👉 #3D scene reconstruction of what a person is observing using only the reflections of their eyes
😎Review https://t.ly/uBO6
😎Paper arxiv.org/pdf/2306.09348.pdf
😎Project https://world-from-eyes.github.io/
👉 #3D scene reconstruction of what a person is observing using only the reflections of their eyes
😎Review https://t.ly/uBO6
😎Paper arxiv.org/pdf/2306.09348.pdf
😎Project https://world-from-eyes.github.io/
🤯28🔥12💩2🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🧿 NeRF-Supervised Deep Stereo 🧿
👉A novel pioneering pipeline for training deep stereo networks WITH NO ground-truth
😎Review https://t.ly/c7j-
😎Project nerfstereo.github.io/
😎Dataset https://amsacta.unibo.it/id/eprint/7218/
😎Code github.com/fabiotosi92/NeRF-Supervised-Deep-Stereo
😎Paper https://openaccess.thecvf.com/content/CVPR2023/papers/Tosi_NeRF-Supervised_Deep_Stereo_CVPR_2023_paper.pdf
👉A novel pioneering pipeline for training deep stereo networks WITH NO ground-truth
😎Review https://t.ly/c7j-
😎Project nerfstereo.github.io/
😎Dataset https://amsacta.unibo.it/id/eprint/7218/
😎Code github.com/fabiotosi92/NeRF-Supervised-Deep-Stereo
😎Paper https://openaccess.thecvf.com/content/CVPR2023/papers/Tosi_NeRF-Supervised_Deep_Stereo_CVPR_2023_paper.pdf
🥰8🤩3❤1👍1💩1😍1
This media is not supported in your browser
VIEW IN TELEGRAM
🫣 Text-Guided Adversarial Makeup 🫣
👉Novel facial privacy protection via adversarial latent codes. Makeup vs Face Recognition.
😎Review https://t.ly/pBCP
😎Paper arxiv.org/pdf/2306.10008.pdf
😎Code github.com/fahadshamshad/Clip2Protect
👉Novel facial privacy protection via adversarial latent codes. Makeup vs Face Recognition.
😎Review https://t.ly/pBCP
😎Paper arxiv.org/pdf/2306.10008.pdf
😎Code github.com/fahadshamshad/Clip2Protect
❤6👍1🔥1🥰1💩1
Media is too big
VIEW IN TELEGRAM
🦷 Few-Shot Geometry-Aware Keypoints 🦷
👉UBC (+Flawless AI) unveils the new SOTA in semantic keypoints localization. Suitable for faces, animals, cars, mouth, teeth & more
😎Review https://t.ly/-0qN
😎Paper arxiv.org/pdf/2303.17216.pdf
😎Project xingzhehe.github.io/FewShot3DKP/
👉UBC (+Flawless AI) unveils the new SOTA in semantic keypoints localization. Suitable for faces, animals, cars, mouth, teeth & more
😎Review https://t.ly/-0qN
😎Paper arxiv.org/pdf/2303.17216.pdf
😎Project xingzhehe.github.io/FewShot3DKP/
🤯10👍4❤2⚡2👏2🤩2🔥1
This media is not supported in your browser
VIEW IN TELEGRAM
🚔 Fooling Neural Forensic Classifiers 🚔
👉Adversarial faces able to fool the forensic classifiers, while remaining undetectable by humans
😎Review https://t.ly/33Cc
😎Paper arxiv.org/pdf/2306.13091.pdf
😎Project koushiksrivats.github.io/face_attribute_attack
😎Code github.com/koushiksrivats/face_attribute_attack
👉Adversarial faces able to fool the forensic classifiers, while remaining undetectable by humans
😎Review https://t.ly/33Cc
😎Paper arxiv.org/pdf/2306.13091.pdf
😎Project koushiksrivats.github.io/face_attribute_attack
😎Code github.com/koushiksrivats/face_attribute_attack
😢6❤4👏2😱2🍾2👍1🤯1😍1
panohead_overview-min.gif
24.3 MB
🍥 PanoHead: 3D Full-Head Synthesis 🍥
👉#ByteDance (+UW-M) unveils PanoHead: 360◦ view-consistent portraits from a single-view image
😎Review https://t.ly/MrLNR
😎Paper arxiv.org/pdf/2303.13071.pdf
😎Project sizhean.github.io/panohead
😎Code github.com/sizhean/panohead
👉#ByteDance (+UW-M) unveils PanoHead: 360◦ view-consistent portraits from a single-view image
😎Review https://t.ly/MrLNR
😎Paper arxiv.org/pdf/2303.13071.pdf
😎Project sizhean.github.io/panohead
😎Code github.com/sizhean/panohead
🔥7❤4🤯3😱1
AI with Papers - Artificial Intelligence & Deep Learning
🀄 Drag-GAN: user-friendly image-manipulation 🀄 👉 Manual deforming of (real and generated) images over pose, shape, expression and layout. 😎Review https://bit.ly/3BFyXlR 😎Paper arxiv.org/pdf/2305.10973.pdf 😎Project vcai.mpi-inf.mpg.de/projects/DragGAN…
Linkedin
#google #artificialintelligence #machinelearning #ml #ai #deeplearning… | Alessandro Ferrari | 40 comments
🔥🔥 Source Code of Drag-GAN IS OUT! 🔥🔥
👉Manual deforming of (real and generated) images over pose, shape, expression and layout. Source Code just released a few hours ago 👇
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Max Planck + MIT + #Google AR/VR = 🤯
✅Supervising handle points to move…
👉Manual deforming of (real and generated) images over pose, shape, expression and layout. Source Code just released a few hours ago 👇
𝐇𝐢𝐠𝐡𝐥𝐢𝐠𝐡𝐭𝐬:
✅Max Planck + MIT + #Google AR/VR = 🤯
✅Supervising handle points to move…
🔥25😱6❤3🥰1🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🔮SAM-PT: Segment Anything+Tracking🔮
👉SAM-PT is the first method to utilize sparse point propagation for Video Object Segmentation (VOS).
😎Review https://t.ly/QLMG
😎Paper arxiv.org/pdf/2307.01197.pdf
😎Project www.vis.xyz/pub/sam-pt/
😎Code github.com/SysCV/sam-pt
👉SAM-PT is the first method to utilize sparse point propagation for Video Object Segmentation (VOS).
😎Review https://t.ly/QLMG
😎Paper arxiv.org/pdf/2307.01197.pdf
😎Project www.vis.xyz/pub/sam-pt/
😎Code github.com/SysCV/sam-pt
🔥14❤7🤯3👍1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🪩 DISCO: Human Dance Generation 🪩
👉NTU (+ #Microsoft) unveils DISCO: a big step towards the Human Dance Generation.
😎Review https://t.ly/cNGX
😎Paper arxiv.org/pdf/2307.00040.pdf
😎Project disco-dance.github.io/
😎Code github.com/Wangt-CN/DisCo
👉NTU (+ #Microsoft) unveils DISCO: a big step towards the Human Dance Generation.
😎Review https://t.ly/cNGX
😎Paper arxiv.org/pdf/2307.00040.pdf
😎Project disco-dance.github.io/
😎Code github.com/Wangt-CN/DisCo
🔥13🥰4😍2⚡1👍1🍾1
This media is not supported in your browser
VIEW IN TELEGRAM
🛣️ STAR.: 3D-tracking w/ attention paradigm 🛣️
👉#Mercedes STAR: e2e 3D object tracking that follows the tracking-by-attention paradigm
😎Review https://t.ly/JoGj
😎Paper arxiv.org/pdf/2306.17602.pdf
😎Project simondoll.github.io/publications/star_track
👉#Mercedes STAR: e2e 3D object tracking that follows the tracking-by-attention paradigm
😎Review https://t.ly/JoGj
😎Paper arxiv.org/pdf/2306.17602.pdf
😎Project simondoll.github.io/publications/star_track
👍14🔥1🥰1👏1
This media is not supported in your browser
VIEW IN TELEGRAM
🍡 Text2Cinemagraphs: Cinemagraph from text 🍡
👉CMU (+ #Snap) unveils a fully automated method for creating cinemagraphs from text descriptions
😎Review https://t.ly/BwZs6
😎Paper arxiv.org/pdf/2307.03190.pdf
😎Project text2cinemagraph.github.io/website
😎Code github.com/text2cinemagraph/text2cinemagraph
👉CMU (+ #Snap) unveils a fully automated method for creating cinemagraphs from text descriptions
😎Review https://t.ly/BwZs6
😎Paper arxiv.org/pdf/2307.03190.pdf
😎Project text2cinemagraph.github.io/website
😎Code github.com/text2cinemagraph/text2cinemagraph
❤12🤯3😱1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🔥Test-Time Training on fire 🔥
👉Extending the TTT to the streaming setting. Suitable for Panoptic, Instance & Colorization.
😎Review https://t.ly/eZYA
😎Paper arxiv.org/pdf/2307.05014.pdf
😎Project https://video-ttt.github.io/
😎Code github.com/renwang435/video-ttt-release
👉Extending the TTT to the streaming setting. Suitable for Panoptic, Instance & Colorization.
😎Review https://t.ly/eZYA
😎Paper arxiv.org/pdf/2307.05014.pdf
😎Project https://video-ttt.github.io/
😎Code github.com/renwang435/video-ttt-release
🔥10👍3⚡1🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
🃏 Deepfake via casual self-scan 🃏
👉TAU presents a novel approach to reenact an ID using only a casual self-scan
😎Review https://t.ly/9T8Wi
😎Paper arxiv.org/pdf/2307.06307.pdf
😎Project arielazary.github.io/PGR
👉TAU presents a novel approach to reenact an ID using only a casual self-scan
😎Review https://t.ly/9T8Wi
😎Paper arxiv.org/pdf/2307.06307.pdf
😎Project arielazary.github.io/PGR
🤯7👍6❤5🔥1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
🎪 Extreme Human Pose Estimation 🎪
👉RePoGen: novel synthetic data generator of extreme/realistic poses of humans
😎Review https://t.ly/ecBvM
😎Paper arxiv.org/pdf/2307.06737.pdf
😎Project mirapurkrabek.github.io/RePoGen-paper
😎Code github.com/MiraPurkrabek/RePoGen
👉RePoGen: novel synthetic data generator of extreme/realistic poses of humans
😎Review https://t.ly/ecBvM
😎Paper arxiv.org/pdf/2307.06737.pdf
😎Project mirapurkrabek.github.io/RePoGen-paper
😎Code github.com/MiraPurkrabek/RePoGen
🔥12👍2👏1🤯1😱1
This media is not supported in your browser
VIEW IN TELEGRAM
💡 DATID-3D: Text-to-3D Generation 💡
👉 A novel domain adaptation method for 3D via text-to-image diffusion. 🤗-Demo available!
😎Review https://t.ly/TCL-B
😎Paper arxiv.org/pdf/2211.16374.pdf
😎Project gwang-kim.github.io/datid_3d/
😎Code github.com/gwang-kim/DATID-3D
🤗 huggingface.co/spaces/gwang-kim/DATID-3D
😎Colab colab.research.google.com/drive/1e9NSVB7x_hjz-nr4K0jO4rfTXILnNGtA?usp=sharing
👉 A novel domain adaptation method for 3D via text-to-image diffusion. 🤗-Demo available!
😎Review https://t.ly/TCL-B
😎Paper arxiv.org/pdf/2211.16374.pdf
😎Project gwang-kim.github.io/datid_3d/
😎Code github.com/gwang-kim/DATID-3D
🤗 huggingface.co/spaces/gwang-kim/DATID-3D
😎Colab colab.research.google.com/drive/1e9NSVB7x_hjz-nr4K0jO4rfTXILnNGtA?usp=sharing
🤯5
This media is not supported in your browser
VIEW IN TELEGRAM
🧯Neural Focal Modulation VAR🧯
👉A novel architecture for video recognition that models both local/global context
😎Review https://t.ly/rF_fk
😎Paper arxiv.org/pdf/2307.06947.pdf
😎Project talalwasim.github.io/Video-FocalNets
😎Code github.com/TalalWasim/Video-FocalNets
👉A novel architecture for video recognition that models both local/global context
😎Review https://t.ly/rF_fk
😎Paper arxiv.org/pdf/2307.06947.pdf
😎Project talalwasim.github.io/Video-FocalNets
😎Code github.com/TalalWasim/Video-FocalNets
🔥8⚡1👏1🤩1
This media is not supported in your browser
VIEW IN TELEGRAM
🐈 Gen-AI as representation learner 🐈
👉DreamTeacher: novel self-supervised feats. representation learning framework that utilizes gen-nets for pre-training downstream image backbones
😎Review https://t.ly/RL8iG
😎Paper arxiv.org/pdf/2307.07487.pdf
😎Project research.nvidia.com/labs/toronto-ai/DreamTeacher
👉DreamTeacher: novel self-supervised feats. representation learning framework that utilizes gen-nets for pre-training downstream image backbones
😎Review https://t.ly/RL8iG
😎Paper arxiv.org/pdf/2307.07487.pdf
😎Project research.nvidia.com/labs/toronto-ai/DreamTeacher
🔥9👍2🤯1
This media is not supported in your browser
VIEW IN TELEGRAM
☔ #SelfDriving? It's all about weather! ☔
👉Novel self-supervised MDE method to handle adverse weather in real-world autonomous driving
😎Review https://t.ly/tcLQW
😎Paper arxiv.org/pdf/2307.08357.pdf
😎Project kieran514.github.io/Robust-Depth-Project/
👉Novel self-supervised MDE method to handle adverse weather in real-world autonomous driving
😎Review https://t.ly/tcLQW
😎Paper arxiv.org/pdf/2307.08357.pdf
😎Project kieran514.github.io/Robust-Depth-Project/
❤7👍3🤯1😱1
🦙 Llama-2: the Open-Source "ChatGPT" 🦙
👉GenAI, #Meta unveils Llama-2: a collection of LLMs ranging in scale 7-70B params. Challenging with #chatgpt, but open.
😎Review https://t.ly/bLJgP
😎Paper https://t.ly/AOXru
😎Project https://ai.meta.com/llama
👉GenAI, #Meta unveils Llama-2: a collection of LLMs ranging in scale 7-70B params. Challenging with #chatgpt, but open.
😎Review https://t.ly/bLJgP
😎Paper https://t.ly/AOXru
😎Project https://ai.meta.com/llama
🤯19❤2🔥1💩1