AI with Papers - Artificial Intelligence & Deep Learning
π Drag-GAN: user-friendly image-manipulation π π Manual deforming of (real and generated) images over pose, shape, expression and layout. πReview https://bit.ly/3BFyXlR πPaper arxiv.org/pdf/2305.10973.pdf πProject vcai.mpi-inf.mpg.de/projects/DragGANβ¦
Linkedin
π₯π₯ Source Code of Drag-GAN IS OUT! | Alessandro Ferrari | 40 comments
π₯π₯ Source Code of Drag-GAN IS OUT! π₯π₯
πManual deforming of (real and generated) images over pose, shape, expression and layout. Source Code just released a few hours ago π
ππ’π π‘π₯π’π π‘ππ¬:
β Max Planck + MIT + #Google AR/VR = π€―
β Supervising handle points to moveβ¦
πManual deforming of (real and generated) images over pose, shape, expression and layout. Source Code just released a few hours ago π
ππ’π π‘π₯π’π π‘ππ¬:
β Max Planck + MIT + #Google AR/VR = π€―
β Supervising handle points to moveβ¦
π₯25π±6β€3π₯°1π€―1
This media is not supported in your browser
VIEW IN TELEGRAM
πͺ Muscles in Action with #AI πͺ
πMuscles in Action (MIA): learn to incorporate muscle activity into human motion representations
πReview https://t.ly/hUKub
πPaper arxiv.org/pdf/2212.02978.pdf
πProject musclesinaction.cs.columbia.edu
πMuscles in Action (MIA): learn to incorporate muscle activity into human motion representations
πReview https://t.ly/hUKub
πPaper arxiv.org/pdf/2212.02978.pdf
πProject musclesinaction.cs.columbia.edu
π₯7π2π2π€―1
This media is not supported in your browser
VIEW IN TELEGRAM
π Multimodal Neural Designer π
π Multimodal #AI that can generate novel fashion images conditioned on text, keypoints, and sketches
πReview https://t.ly/zVk70
πPaper arxiv.org/pdf/2304.02051.pdf
πCode github.com/aimagelab/multimodal-garment-designer
π Multimodal #AI that can generate novel fashion images conditioned on text, keypoints, and sketches
πReview https://t.ly/zVk70
πPaper arxiv.org/pdf/2304.02051.pdf
πCode github.com/aimagelab/multimodal-garment-designer
π₯°6β€4π€©3π₯2β‘1
This media is not supported in your browser
VIEW IN TELEGRAM
𧱠Generating Scenes from Touch π§±
π#AI for synthesizing images from tactile signals (and vice versa) and apply it to a number of visuo-tactile synthesis tasks
πReview https://t.ly/Gxr0L
πPaper https://arxiv.org/pdf/2309.15117.pdf
πProject https://fredfyyang.github.io/vision-from-touch
πCode https://github.com/fredfyyang/vision-from-touch
π#AI for synthesizing images from tactile signals (and vice versa) and apply it to a number of visuo-tactile synthesis tasks
πReview https://t.ly/Gxr0L
πPaper https://arxiv.org/pdf/2309.15117.pdf
πProject https://fredfyyang.github.io/vision-from-touch
πCode https://github.com/fredfyyang/vision-from-touch
π€―9π6β€1π₯1π1π±1
This media is not supported in your browser
VIEW IN TELEGRAM
π± Making LLaMA See and Draw π±
πTencent #AI planted a SEED of Vision in Large Language Model. Making LLaMA see 'n' draw stuff.
πReview https://t.ly/QiCAv
πPaper arxiv.org/pdf/2310.01218.pdf
πCode github.com/AILab-CVC/SEED
πTencent #AI planted a SEED of Vision in Large Language Model. Making LLaMA see 'n' draw stuff.
πReview https://t.ly/QiCAv
πPaper arxiv.org/pdf/2310.01218.pdf
πCode github.com/AILab-CVC/SEED
β€8π4π€―3π₯1
π TextPSG: PSG from Text π
πA novel problem in #AI: Panoptic Scene Graph Generation from Purely Textual Descriptions (Caption-toPSG)
πReview https://t.ly/UXEmk
πPaper arxiv.org/pdf/2310.07056.pdf
πProject vis-www.cs.umass.edu/TextPSG
πCode github.com/chengyzhao/TextPSG
πA novel problem in #AI: Panoptic Scene Graph Generation from Purely Textual Descriptions (Caption-toPSG)
πReview https://t.ly/UXEmk
πPaper arxiv.org/pdf/2310.07056.pdf
πProject vis-www.cs.umass.edu/TextPSG
πCode github.com/chengyzhao/TextPSG
π₯9β€5π3π€©1
π¦ΉββοΈ Snap's Hyper-Realistic Human π¦ΉββοΈ
πNew diffusive #AI by Snap that generates in-the-wild human images with hyper-realism. Swipe the gallery, NUTS!π
πGallery https://t.ly/cG74X
πPaper arxiv.org/pdf/2310.08579.pdf
πProject snap-research.github.io/HyperHuman
πCode github.com/snap-research/HyperHuman
πNew diffusive #AI by Snap that generates in-the-wild human images with hyper-realism. Swipe the gallery, NUTS!π
πGallery https://t.ly/cG74X
πPaper arxiv.org/pdf/2310.08579.pdf
πProject snap-research.github.io/HyperHuman
πCode github.com/snap-research/HyperHuman
π4π₯1π€―1π±1π€©1π€£1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯»SF: Towards Virtual Clothπ₯»
πSEA AI Lab unveils a novel #AI to recovery the garment sewing patterns from daily photos for #AR / #VR worlds
πReview https://t.ly/MwpAV
πProject https://sewformer.github.io/
πPaper https://arxiv.org/pdf/2311.04218.pdf
πCode https://github.com/sail-sg/sewformer
πSEA AI Lab unveils a novel #AI to recovery the garment sewing patterns from daily photos for #AR / #VR worlds
πReview https://t.ly/MwpAV
πProject https://sewformer.github.io/
πPaper https://arxiv.org/pdf/2311.04218.pdf
πCode https://github.com/sail-sg/sewformer
π4π₯2π₯°2π2π€―1π€©1
This media is not supported in your browser
VIEW IN TELEGRAM
π₯ Hu.ma.ne #AI Pin is out! π₯
πHu.ma.ne just launched #AI Pin: the new standalone AI-powered screenless device. Running on the GPT-4 LLMs, suitable for real-time translation. #AI-powered camera and laser projector
π More https://t.ly/IvoN7
πHu.ma.ne just launched #AI Pin: the new standalone AI-powered screenless device. Running on the GPT-4 LLMs, suitable for real-time translation. #AI-powered camera and laser projector
π More https://t.ly/IvoN7
β€6π₯4π©2π1π±1
This media is not supported in your browser
VIEW IN TELEGRAM
𧱠Material Palette from Images π§±
πA novel problem in #AI: material extraction from a real-world image without any prior knowledge π€―
πDiscussion https://t.ly/AIWs-
πPaper https://lnkd.in/dBFAVWPF
πProject https://lnkd.in/dV5jK8Sm
πCode https://lnkd.in/dNhMnfFb
πDataset (coming) ...
πA novel problem in #AI: material extraction from a real-world image without any prior knowledge π€―
πDiscussion https://t.ly/AIWs-
πPaper https://lnkd.in/dBFAVWPF
πProject https://lnkd.in/dV5jK8Sm
πCode https://lnkd.in/dNhMnfFb
πDataset (coming) ...
β€9π2π₯1π₯°1π€―1
This media is not supported in your browser
VIEW IN TELEGRAM
π HD Generative #AI With No $$π
πDemoFusion: a novel approach for HD image generation w/ no money. Progressive Upscaling, Skip Residual, & Dilated Sampling to achieve higher-resolution ever π₯
πReview https://t.ly/sIqDV
πPaper https://lnkd.in/deDt-zcK
πProject https://lnkd.in/dFGj47Xw
πCode https://lnkd.in/dY3UcXwp
πDemoFusion: a novel approach for HD image generation w/ no money. Progressive Upscaling, Skip Residual, & Dilated Sampling to achieve higher-resolution ever π₯
πReview https://t.ly/sIqDV
πPaper https://lnkd.in/deDt-zcK
πProject https://lnkd.in/dFGj47Xw
πCode https://lnkd.in/dY3UcXwp
π4β€2π€―2π1π±1