EMO: Emote Portrait Alive - Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions
Paper
ā¢
2402.17485
ā¢
Published
ā¢
182
š Avatars
The latest AI-powered technologies usher in a new era of realistic avatars! š
Note š® Post: https://huggingface.co/posts/DmitryRyumin/146398971160140 š Paper: https://huggingface.co/papers/2402.17485 š Github Page: https://humanaigc.github.io/emote-portrait-alive š Repository: https://github.com/HumanAIGC/EMO
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior
Paper ā¢ 2312.01841 ā¢ Published ā¢ 1Note š Paper: https://huggingface.co/papers/2312.01841 š Github Page: https://humanaigc.github.io/vivid-talk š Repository: https://github.com/HumanAIGC/VividTalk šŗ Video: https://www.youtube.com/watch?v=lJVzt7JCe_4
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Paper ā¢ 2311.16498 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/578997477674932 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š¤ Demo: https://huggingface.co/spaces/zcxu-eric/magicanimate š Paper: https://huggingface.co/papers/2311.16498 š Github Page: https://showlab.github.io/magicanimate/ š Repository: https://github.com/magic-research/magic-animate š„ Model š¤: https://huggingface.co/zcxu-eric/MagicAnimate
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
Paper ā¢ 2312.02134 ā¢ Published ā¢ 2Note š® Post: https://huggingface.co/posts/DmitryRyumin/635360328098616 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2312.02134 š Github Page: https://huliangxiao.github.io/GaussianAvatar š Repository: https://github.com/huliangxiao/GaussianAvatar šŗ Video: https://www.youtube.com/watch?v=a4g8Z9nCF-k
SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
Paper ā¢ 2311.17590 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/733100901107547 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2311.17590 š Github Page: https://ziqiaopeng.github.io/synctalk š Repository: https://github.com/ZiqiaoPeng/SyncTalk
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Paper ā¢ 2401.08503 ā¢ Published ā¢ 3Note š® Post: https://huggingface.co/posts/DmitryRyumin/170929653134354 š Conference: ICLR, May 7-11, 2024 | Vienna, Austria š¦š¹ š Paper: https://huggingface.co/papers/2401.08503 š Github Page: https://real3dportrait.github.io/ š Repository: https://github.com/yerfor/Real3DPortrait š„ Model š¤: https://huggingface.co/ameerazam08/Real3DPortrait
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Paper ā¢ 2401.10215 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/289967366439346 š Conference: ICLR, May 7-11, 2024 | Vienna, Austria š¦š¹ š Paper: https://huggingface.co/papers/2401.10215 š Github Page: https://xg-chu.github.io/project_gpavatar š Repository: https://github.com/xg-chu/GPAvatar šŗ Video: https://www.youtube.com/watch?v=7A3DMaB6Zk0
Relightable and Animatable Neural Avatars from Videos
Paper ā¢ 2312.12877 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/188560282332993 š Conference: AAAI, February 20-27, 2024 | Vancouver, Canada šØš¦ š Paper: https://huggingface.co/papers/2312.12877 š Github Page: https://wenbin-lin.github.io/RelightableAvatar-page š Repository: https://github.com/wenbin-lin/RelightableAvatar šŗ Video: https://www.youtube.com/watch?v=v9rlys0xQGo
High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
Paper ā¢ 2310.06275 ā¢ Published ā¢ 2Note š Conference: AAAI, February 20-27, 2024 | Vancouver, Canada šØš¦ š Paper: https://huggingface.co/papers/2310.06275 š Github Page: https://minghanqin.github.io/AvatarSVE/ š Repository: https://github.com/minghanqin/AvatarSVE šŗ Video: https://www.youtube.com/watch?v=dPgAa-6Kt8Q
VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
Paper ā¢ 2403.08764 ā¢ Published ā¢ 34Note š® Post: https://huggingface.co/posts/DmitryRyumin/888482747169050 š Paper: https://huggingface.co/papers/2403.08764 š Github Page: https://enriccorona.github.io/vlogger/
Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
Paper ā¢ 2311.16096 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/496583626851543 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2311.16096 š Github Page: https://animatable-gaussians.github.io š Repository: https://github.com/lizhe00/AnimatableGaussians šŗ Video: https://www.youtube.com/watch?v=kOmZxD0HxZI
NECA: Neural Customizable Human Avatar
Paper ā¢ 2403.10335 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/399329903001758 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2403.10335 š Repository: https://github.com/iSEE-Laboratory/NECA
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
Paper ā¢ 2311.02826 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/288502341253111 š Conference: ICLR, May 7-11, 2024 | Vienna, Austria š¦š¹ š Paper: https://huggingface.co/papers/2311.02826 š Github Page: https://mybabyyh.github.io/InstructPix2NeRF š Repository: https://github.com/mybabyyh/InstructPix2NeRF
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
Paper ā¢ 2312.03029 ā¢ Published ā¢ 22Note š® Post: https://huggingface.co/posts/DmitryRyumin/685682060907396 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2312.03029 š Github Page: https://yuelangx.github.io/gaussianheadavatar š Repository: https://github.com/YuelangX/Gaussian-Head-Avatar šŗ Video: https://www.youtube.com/watch?v=kvrrI3EoM5g
GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
Paper ā¢ 2312.02069 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/619817116350533 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2312.02069 š Github Page: https://shenhanqian.github.io/gaussian-avatars š Repository: https://github.com/ShenhanQian/GaussianAvatars šŗ Video: https://www.youtube.com/watch?v=lVEY78RwU_I
Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute
Paper ā¢ 2401.00711 ā¢ Published ā¢ 2Note š® Post: https://huggingface.co/posts/DmitryRyumin/595207139085023 š Conference: ICASSP, 14-19 April 2024 | Seoul, Korea š°š· š Paper: https://huggingface.co/papers/2401.00711 š Github Page: https://iecqgong.github.io/text2avatar/
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
Paper ā¢ 2403.17008 ā¢ Published ā¢ 17Note š® Post: https://huggingface.co/posts/DmitryRyumin/204103548247572 š Paper: https://huggingface.co/papers/2403.17008 š Github Page: https://jshilong.github.io/flashface-page/
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
Paper ā¢ 2403.17694 ā¢ Published ā¢ 10Note š® Post: https://huggingface.co/posts/DmitryRyumin/191716706611860 š¤ Demo: https://huggingface.co/spaces/ZJYang/AniPortrait_official š Paper: https://huggingface.co/papers/2403.17694 š Repository: https://github.com/Zejun-Yang/AniPortrait š„ Model š¤: https://huggingface.co/ZJYang/AniPortrait
Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
Paper ā¢ 2404.01543 ā¢ Published ā¢ 3Note š® Post: https://huggingface.co/posts/DmitryRyumin/763522030257659 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2404.01543 š Github Page: https://augmentedperception.github.io/monoavatar-plus/
GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image
Paper ā¢ 2404.02152 ā¢ Published ā¢ 3Note š® Post: https://huggingface.co/posts/DmitryRyumin/335365529548063 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2404.02152 š Github Page: https://zju3dv.github.io/geneavatar/ š Repository: https://github.com/zju3dv/GeneAvatar šŗ Video: https://www.youtube.com/watch?v=4zfbfPivtVU
3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
Paper ā¢ 2312.09228 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/381309144455409 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2312.09228 š Github Page: https://neuralbodies.github.io/3DGS-Avatar/ š Repository: https://github.com/mikeqzy/3dgs-avatar-release šŗ Video: https://www.youtube.com/watch?v=FJ29U9OkmmU
InstructHumans: Editing Animated 3D Human Textures with Instructions
Paper ā¢ 2404.04037 ā¢ PublishedNote š® Post: https://huggingface.co/posts/DmitryRyumin/462458353486294 š Paper: https://huggingface.co/papers/2404.04037 š Web Page: https://jyzhu.top/instruct-humans/ š Repository: https://github.com/viridityzhu/InstructHumans
PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Paper ā¢ 2404.04421 ā¢ Published ā¢ 14Note š® Post: https://huggingface.co/posts/DmitryRyumin/930608949502580 š Paper: https://huggingface.co/papers/2404.04421 š GitHub Page: https://qingqing-zhao.github.io/PhysAvatar
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
Paper ā¢ 2404.07991 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/532264219296718 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2404.07991 š Github Page: https://wenj.github.io/GoMAvatar/ š Repository: https://github.com/wenj/GoMAvatar
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper ā¢ 2404.10667 ā¢ Published ā¢ 11Note š Paper: https://huggingface.co/papers/2404.10667 š Web Page: https://www.microsoft.com/en-us/research/project/vasa-1/
HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach
Paper ā¢ 2404.01094 ā¢ Published ā¢ 3Note š® Post: https://huggingface.co/posts/DmitryRyumin/932263322939776 š¤ Demo: https://huggingface.co/spaces/multimodalart/hairfastgan š Paper: https://huggingface.co/papers/2404.01094 š Repository: https://github.com/AIRI-Institute/HairFastGAN š„ Model š¤: https://huggingface.co/AIRI-Institute/HairFastGAN
Learn2Talk: 3D Talking Face Learns from 2D Talking Face
Paper ā¢ 2404.12888 ā¢ Published ā¢ 2Note š® Post: https://huggingface.co/posts/DmitryRyumin/511657668327096 š Paper: https://huggingface.co/papers/2404.12888 š Github Page: https://lkjkjoiuiu.github.io/Learn2Talk/
WANDR: Intention-guided Human Motion Generation
Paper ā¢ 2404.15383 ā¢ PublishedNote š® Post: https://huggingface.co/posts/DmitryRyumin/295452758814429 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2404.15383 š Web Page: https://wandr.is.tue.mpg.de š Repository: https://github.com/markos-diomataris/wandr šŗ Video: https://www.youtube.com/watch?v=9szizM-XUCg
ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving
Paper ā¢ 2404.16771 ā¢ Published ā¢ 16Note š® Post: https://huggingface.co/posts/DmitryRyumin/303634956982953 š Paper: https://huggingface.co/papers/2404.16771 š Github Page: https://ssugarwh.github.io/consistentid.github.io/ š Repository: https://github.com/JackAILab/ConsistentID
EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars
Paper ā¢ 2404.19110 ā¢ Published ā¢ 2Note š® Post: https://huggingface.co/posts/DmitryRyumin/113952082634225 š Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA šŗšø š Paper: https://huggingface.co/papers/2404.19110 š Github Page: https://neeek2303.github.io/EMOPortraits
3D Gaussian Blendshapes for Head Avatar Animation
Paper ā¢ 2404.19398 ā¢ Published ā¢ 1Note š® Post: https://huggingface.co/posts/DmitryRyumin/802475347987275 š Conference: SIGGRAPH, 28 Jul ā 1 Aug, 2024 | Denver CO, USA šŗšø š Paper: https://huggingface.co/papers/2404.19398 š Github Page: https://gapszju.github.io/GaussianBlendshape/