Trending AI news stories + papers https://t.co/OwQ4jKArOL pic.twitter.com/K9LUxtzPMK
— AK (@_akhaliq) 4 juillet 2023
Trending AI news stories + papers https://
open.substack.com/pub/akhaliq/p/
trending-ai-news-stories-papers-807
…
@_akhaliq
-
Trending AI News Stories and Papers
By
–
-
Baroque Space Opera Generated with Zeroscope AI
By
–
baroque space opera
— AK (@_akhaliq) 4 juillet 2023
zeroscope text to video AI by @veryVANYA pic.twitter.com/piBiQjnCzAbaroque space opera zeroscope text to video AI by @veryVANYA
-
Zeroscope XL Text to Video Demo Released by fffiloni
By
–
Zeroscope XL text to video demo by @fffiloni is out
— AK (@_akhaliq) 4 juillet 2023
demo: https://t.co/YCHBI85uVZ pic.twitter.com/dVJ2lXRn7WZeroscope XL text to video demo by @fffiloni is out demo: https://
huggingface.co/spaces/fffilon
i/zeroscope-XL
… -
Unofficial PyTorch Implementation of StyleDrop Text-to-Image Generation
By
–
unofficial PyTorch implementation of StyleDrop: Text-to-Image Generation in Any Style github: https://
github.com/zideliu/StyleD
rop-PyTorch
… -
Real-time Monocular Full-body Motion Capture via Sequential Learning
By
–
Real-time Monocular Full-body Capture in World Space via Sequential Proxy-to-Motion Learning paper page: https://
huggingface.co/papers/2307.01
200
… Learning-based approaches to monocular motion capture have recently shown promising results by learning to regress in a data-driven manner. However, -
Segment Anything Meets Point Tracking: SAM-PT Model
By
–
Segment Anything Meets Point Tracking
— AK (@_akhaliq) 4 juillet 2023
paper page: https://t.co/NCXpZz6ifd
The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, employing interactive prompts such as points to generate masks. This paper presents SAM-PT, a… pic.twitter.com/1kKzl3FnUMSegment Anything Meets Point Tracking paper page: https://
huggingface.co/papers/2307.01
197
… The Segment Anything Model (SAM) has established itself as a powerful zero-shot image segmentation model, employing interactive prompts such as points to generate masks. This paper presents SAM-PT, a -
SketchMetaFace: Learning-based Interface for 3D Character Face Modeling
By
–
SketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling
— AK (@_akhaliq) 4 juillet 2023
paper page: https://t.co/kh6gTS5yWR
Modeling 3D avatars benefits various application scenarios such as AR/VR, gaming, and filming. Character faces contribute significant diversity… pic.twitter.com/b322anqpmCSketchMetaFace: A Learning-based Sketching Interface for High-fidelity 3D Character Face Modeling paper page: https://
huggingface.co/papers/2307.00
804
… Modeling 3D avatars benefits various application scenarios such as AR/VR, gaming, and filming. Character faces contribute significant diversity -
DisCo: Disentangled Control for Human Dance Generation
By
–
DisCo: Disentangled Control for Referring Human Dance Generation in Real World
— AK (@_akhaliq) 4 juillet 2023
paper page: https://t.co/bL1fWJCLcs
Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it… pic.twitter.com/qmZYkzyx4UDisCo: Disentangled Control for Referring Human Dance Generation in Real World paper page: https://
huggingface.co/papers/2307.00
040
… Generative AI has made significant strides in computer vision, particularly in image/video synthesis conditioned on text descriptions. Despite the advancements, it -
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
By
–
LEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance
— AK (@_akhaliq) 4 juillet 2023
paper page: https://t.co/dmwUU4z70h
demo: https://t.co/JCb5rXheLL
Recent large-scale text-guided diffusion models provide powerful image-generation capabilities. Currently, a significant effort is given to… pic.twitter.com/I8gUlILaDPLEDITS: Real Image Editing with DDPM Inversion and Semantic Guidance paper page: https://
huggingface.co/papers/2307.00
522
…
demo: https://
huggingface.co/spaces/editing
-images/ledits
… Recent large-scale text-guided diffusion models provide powerful image-generation capabilities. Currently, a significant effort is given to -
MVDiffusion: Multi-view Image Generation with Correspondence-Aware Diffusion
By
–
MVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion
— AK (@_akhaliq) 4 juillet 2023
paper page: https://t.co/QXHUkIC7x2
paper introduces MVDiffusion, a simple yet effective multi-view image generation method for scenarios where pixel-to-pixel correspondences are… pic.twitter.com/zzqvc7f7aBMVDiffusion: Enabling Holistic Multi-view Image Generation with Correspondence-Aware Diffusion paper page: https://
huggingface.co/papers/2307.01
097
… paper introduces MVDiffusion, a simple yet effective multi-view image generation method for scenarios where pixel-to-pixel correspondences are