๐ญ Avatars
The latest AI-powered technologies usher in a new era of realistic avatars! ๐
Paper โข 2402.17485 โข Published โข 190Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/146398971160140 ๐ Paper: https://huggingface.co/papers/2402.17485 ๐ Github Page: https://humanaigc.github.io/emote-portrait-alive ๐ Repository: https://github.com/HumanAIGC/EMO
VividTalk: One-Shot Audio-Driven Talking Head Generation Based on 3D Hybrid Prior
Paper โข 2312.01841 โข Published โข 1Note ๐ Paper: https://huggingface.co/papers/2312.01841 ๐ Github Page: https://humanaigc.github.io/vivid-talk ๐ Repository: https://github.com/HumanAIGC/VividTalk ๐บ Video: https://www.youtube.com/watch?v=lJVzt7JCe_4
MagicAnimate: Temporally Consistent Human Image Animation using Diffusion Model
Paper โข 2311.16498 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/578997477674932 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ค Demo: https://huggingface.co/spaces/zcxu-eric/magicanimate ๐ Paper: https://huggingface.co/papers/2311.16498 ๐ Github Page: https://showlab.github.io/magicanimate/ ๐ Repository: https://github.com/magic-research/magic-animate ๐ฅ Model ๐ค: https://huggingface.co/zcxu-eric/MagicAnimate
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians
Paper โข 2312.02134 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/635360328098616 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.02134 ๐ Github Page: https://huliangxiao.github.io/GaussianAvatar ๐ Repository: https://github.com/huliangxiao/GaussianAvatar ๐บ Video: https://www.youtube.com/watch?v=a4g8Z9nCF-k
SyncTalk: The Devil is in the Synchronization for Talking Head Synthesis
Paper โข 2311.17590 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/733100901107547 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2311.17590 ๐ Github Page: https://ziqiaopeng.github.io/synctalk ๐ Repository: https://github.com/ZiqiaoPeng/SyncTalk
Real3D-Portrait: One-shot Realistic 3D Talking Portrait Synthesis
Paper โข 2401.08503 โข Published โข 4Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/170929653134354 ๐ Conference: ICLR, May 7-11, 2024 | Vienna, Austria ๐ฆ๐น ๐ Paper: https://huggingface.co/papers/2401.08503 ๐ Github Page: https://real3dportrait.github.io/ ๐ Repository: https://github.com/yerfor/Real3DPortrait ๐ฅ Model ๐ค: https://huggingface.co/ameerazam08/Real3DPortrait
GPAvatar: Generalizable and Precise Head Avatar from Image(s)
Paper โข 2401.10215 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/289967366439346 ๐ Conference: ICLR, May 7-11, 2024 | Vienna, Austria ๐ฆ๐น ๐ Paper: https://huggingface.co/papers/2401.10215 ๐ Github Page: https://xg-chu.github.io/project_gpavatar ๐ Repository: https://github.com/xg-chu/GPAvatar ๐บ Video: https://www.youtube.com/watch?v=7A3DMaB6Zk0
Relightable and Animatable Neural Avatars from Videos
Paper โข 2312.12877 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/188560282332993 ๐ Conference: AAAI, February 20-27, 2024 | Vancouver, Canada ๐จ๐ฆ ๐ Paper: https://huggingface.co/papers/2312.12877 ๐ Github Page: https://wenbin-lin.github.io/RelightableAvatar-page ๐ Repository: https://github.com/wenbin-lin/RelightableAvatar ๐บ Video: https://www.youtube.com/watch?v=v9rlys0xQGo
High-Fidelity 3D Head Avatars Reconstruction through Spatially-Varying Expression Conditioned Neural Radiance Field
Paper โข 2310.06275 โข Published โข 2Note ๐ Conference: AAAI, February 20-27, 2024 | Vancouver, Canada ๐จ๐ฆ ๐ Paper: https://huggingface.co/papers/2310.06275 ๐ Github Page: https://minghanqin.github.io/AvatarSVE/ ๐ Repository: https://github.com/minghanqin/AvatarSVE ๐บ Video: https://www.youtube.com/watch?v=dPgAa-6Kt8Q
VLOGGER: Multimodal Diffusion for Embodied Avatar Synthesis
Paper โข 2403.08764 โข Published โข 36Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/888482747169050 ๐ Paper: https://huggingface.co/papers/2403.08764 ๐ Github Page: https://enriccorona.github.io/vlogger/
Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling
Paper โข 2311.16096 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/496583626851543 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2311.16096 ๐ Github Page: https://animatable-gaussians.github.io ๐ Repository: https://github.com/lizhe00/AnimatableGaussians ๐บ Video: https://www.youtube.com/watch?v=kOmZxD0HxZI
NECA: Neural Customizable Human Avatar
Paper โข 2403.10335 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/399329903001758 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2403.10335 ๐ Repository: https://github.com/iSEE-Laboratory/NECA
InstructPix2NeRF: Instructed 3D Portrait Editing from a Single Image
Paper โข 2311.02826 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/288502341253111 ๐ Conference: ICLR, May 7-11, 2024 | Vienna, Austria ๐ฆ๐น ๐ Paper: https://huggingface.co/papers/2311.02826 ๐ Github Page: https://mybabyyh.github.io/InstructPix2NeRF ๐ Repository: https://github.com/mybabyyh/InstructPix2NeRF
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians
Paper โข 2312.03029 โข Published โข 23Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/685682060907396 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.03029 ๐ Github Page: https://yuelangx.github.io/gaussianheadavatar ๐ Repository: https://github.com/YuelangX/Gaussian-Head-Avatar ๐บ Video: https://www.youtube.com/watch?v=kvrrI3EoM5g
GaussianAvatars: Photorealistic Head Avatars with Rigged 3D Gaussians
Paper โข 2312.02069 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/619817116350533 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.02069 ๐ Github Page: https://shenhanqian.github.io/gaussian-avatars ๐ Repository: https://github.com/ShenhanQian/GaussianAvatars ๐บ Video: https://www.youtube.com/watch?v=lVEY78RwU_I
Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute
Paper โข 2401.00711 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/595207139085023 ๐ Conference: ICASSP, 14-19 April 2024 | Seoul, Korea ๐ฐ๐ท ๐ Paper: https://huggingface.co/papers/2401.00711 ๐ Github Page: https://iecqgong.github.io/text2avatar/
FlashFace: Human Image Personalization with High-fidelity Identity Preservation
Paper โข 2403.17008 โข Published โข 19Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/204103548247572 ๐ Paper: https://huggingface.co/papers/2403.17008 ๐ Github Page: https://jshilong.github.io/flashface-page/
AniPortrait: Audio-Driven Synthesis of Photorealistic Portrait Animation
Paper โข 2403.17694 โข Published โข 10Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/191716706611860 ๐ค Demo: https://huggingface.co/spaces/ZJYang/AniPortrait_official ๐ Paper: https://huggingface.co/papers/2403.17694 ๐ Repository: https://github.com/Zejun-Yang/AniPortrait ๐ฅ Model ๐ค: https://huggingface.co/ZJYang/AniPortrait
Efficient 3D Implicit Head Avatar with Mesh-anchored Hash Table Blendshapes
Paper โข 2404.01543 โข Published โข 3Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/763522030257659 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.01543 ๐ Github Page: https://augmentedperception.github.io/monoavatar-plus/
GeneAvatar: Generic Expression-Aware Volumetric Head Avatar Editing from a Single Image
Paper โข 2404.02152 โข Published โข 3Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/335365529548063 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.02152 ๐ Github Page: https://zju3dv.github.io/geneavatar/ ๐ Repository: https://github.com/zju3dv/GeneAvatar ๐บ Video: https://www.youtube.com/watch?v=4zfbfPivtVU
3DGS-Avatar: Animatable Avatars via Deformable 3D Gaussian Splatting
Paper โข 2312.09228 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/381309144455409 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.09228 ๐ Github Page: https://neuralbodies.github.io/3DGS-Avatar/ ๐ Repository: https://github.com/mikeqzy/3dgs-avatar-release ๐บ Video: https://www.youtube.com/watch?v=FJ29U9OkmmU
InstructHumans: Editing Animated 3D Human Textures with Instructions
Paper โข 2404.04037 โข PublishedNote ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/462458353486294 ๐ Paper: https://huggingface.co/papers/2404.04037 ๐ Web Page: https://jyzhu.top/instruct-humans/ ๐ Repository: https://github.com/viridityzhu/InstructHumans
PhysAvatar: Learning the Physics of Dressed 3D Avatars from Visual Observations
Paper โข 2404.04421 โข Published โข 16Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/930608949502580 ๐ Paper: https://huggingface.co/papers/2404.04421 ๐ GitHub Page: https://qingqing-zhao.github.io/PhysAvatar
GoMAvatar: Efficient Animatable Human Modeling from Monocular Video Using Gaussians-on-Mesh
Paper โข 2404.07991 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/532264219296718 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.07991 ๐ Github Page: https://wenj.github.io/GoMAvatar/ ๐ Repository: https://github.com/wenj/GoMAvatar
VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time
Paper โข 2404.10667 โข Published โข 18Note ๐ Paper: https://huggingface.co/papers/2404.10667 ๐ 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 โข 2404.01094 โข Published โข 5Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/932263322939776 ๐ค Demo: https://huggingface.co/spaces/multimodalart/hairfastgan ๐ Paper: https://huggingface.co/papers/2404.01094 ๐ Repository: https://github.com/AIRI-Institute/HairFastGAN ๐ฅ Model ๐ค: https://huggingface.co/AIRI-Institute/HairFastGAN
Learn2Talk: 3D Talking Face Learns from 2D Talking Face
Paper โข 2404.12888 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/511657668327096 ๐ Paper: https://huggingface.co/papers/2404.12888 ๐ Github Page: https://lkjkjoiuiu.github.io/Learn2Talk/
WANDR: Intention-guided Human Motion Generation
Paper โข 2404.15383 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/295452758814429 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.15383 ๐ Web Page: https://wandr.is.tue.mpg.de ๐ Repository: https://github.com/markos-diomataris/wandr ๐บ Video: https://www.youtube.com/watch?v=9szizM-XUCg
ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving
Paper โข 2404.16771 โข Published โข 16Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/303634956982953 ๐ Paper: https://huggingface.co/papers/2404.16771 ๐ Github Page: https://ssugarwh.github.io/consistentid.github.io/ ๐ Repository: https://github.com/JackAILab/ConsistentID
EMOPortraits: Emotion-enhanced Multimodal One-shot Head Avatars
Paper โข 2404.19110 โข Published โข 3Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/113952082634225 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.19110 ๐ Github Page: https://neeek2303.github.io/EMOPortraits
3D Gaussian Blendshapes for Head Avatar Animation
Paper โข 2404.19398 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/802475347987275 ๐ Conference: SIGGRAPH, 28 Jul โ 1 Aug, 2024 | Denver CO, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2404.19398 ๐ Github Page: https://gapszju.github.io/GaussianBlendshape/
AniTalker: Animate Vivid and Diverse Talking Faces through Identity-Decoupled Facial Motion Encoding
Paper โข 2405.03121 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/698577433443867 ๐ Paper: https://huggingface.co/papers/2405.03121 ๐ Github Page: https://x-lance.github.io/AniTalker ๐ Repository: https://github.com/X-LANCE/AniTalker
LayGA: Layered Gaussian Avatars for Animatable Clothing Transfer
Paper โข 2405.07319 โข PublishedNote ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/182984250825015 ๐ Conference: SIGGRAPH, 28 Jul โ 1 Aug, 2024 | Denver CO, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2405.07319 ๐ Github Page: https://jsnln.github.io/layga/index.html
Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
Paper โข 2405.12069 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/557611713480917 ๐ Paper: https://huggingface.co/papers/2405.12069 ๐ Github Page: https://gaussian-head-shoulders.netlify.app
InstructAvatar: Text-Guided Emotion and Motion Control for Avatar Generation
Paper โข 2405.15758 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/378045093988402 ๐ Paper: https://huggingface.co/papers/2405.15758 ๐ Github Page: https://wangyuchi369.github.io/InstructAvatar/ ๐ Repository: https://github.com/wangyuchi369/InstructAvatar
Human4DiT: Free-view Human Video Generation with 4D Diffusion Transformer
Paper โข 2405.17405 โข Published โข 14Note ๐ Paper: https://huggingface.co/papers/2405.17405 ๐ Github Page: https://human4dit.github.io/
Relightable Gaussian Codec Avatars
Paper โข 2312.03704 โข Published โข 29Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/998191475426468 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.03704 ๐ Github Page: https://shunsukesaito.github.io/rgca/
GMTalker: Gaussian Mixture based Emotional talking video Portraits
Paper โข 2312.07669 โข Published โข 1Note ๐ Paper: https://huggingface.co/papers/2312.07669 ๐ Github Page: https://bob35buaa.github.io/GMTalker ๐บ Video: https://www.youtube.com/watch?v=8kcYw3Ps48w
NPGA: Neural Parametric Gaussian Avatars
Paper โข 2405.19331 โข Published โข 10Note ๐ Paper: https://huggingface.co/papers/2405.19331 ๐ Github Page: https://simongiebenhain.github.io/NPGA/ ๐บ Video: https://www.youtube.com/watch?v=NGRxAYbIkus
Learning One-Shot 4D Head Avatar Synthesis using Synthetic Data
Paper โข 2311.18729 โข PublishedNote ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2311.18729 ๐ Github Page: https://yudeng.github.io/Portrait4D/ ๐ Repository: https://github.com/YuDeng/Portrait-4D ๐บ Video: https://www.youtube.com/watch?v=8f1NBTdhvzw
Portrait4D-v2: Pseudo Multi-View Data Creates Better 4D Head Synthesizer
Paper โข 2403.13570 โข Published โข 3Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/891674447263162 ๐ Paper: https://huggingface.co/papers/2403.13570 ๐ Github Page: https://yudeng.github.io/Portrait4D-v2/ ๐ Repository: https://github.com/YuDeng/Portrait-4D ๐บ Video: https://www.youtube.com/watch?v=5YJY6-wcOJo
Stratified Avatar Generation from Sparse Observations
Paper โข 2405.20786 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2405.20786 ๐ Github Page: https://fhan235.github.io/SAGENet/ ๐ Repository: https://github.com/Wenchao-M/SAGE ๐บ Video: https://www.youtube.com/watch?v=RkXaxyv1TOU
Human 3Diffusion: Realistic Avatar Creation via Explicit 3D Consistent Diffusion Models
Paper โข 2406.08475 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2406.08475 ๐ Github Page: https://yuxuan-xue.com/human-3diffusion/ ๐ Repository: https://github.com/YuxuanSnow/Human3Diffusion/
Instant 3D Human Avatar Generation using Image Diffusion Models
Paper โข 2406.07516 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2406.07516 ๐ Github Page: https://www.nikoskolot.com/avatarpopup/
Topo4D: Topology-Preserving Gaussian Splatting for High-Fidelity 4D Head Capture
Paper โข 2406.00440 โข PublishedNote ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/753056979023615 ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2406.00440 ๐ Github Page: https://xuanchenli.github.io/Topo4D/ ๐ Repository: https://github.com/XuanchenLi/Topo4D
Expressive Gaussian Human Avatars from Monocular RGB Video
Paper โข 2407.03204 โข Published โข 1Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/852656118525688 ๐ Paper: https://huggingface.co/papers/2407.03204 ๐ Github Page: https://evahuman.github.io/ ๐ Repository: https://github.com/evahuman/EVA
LivePortrait: Efficient Portrait Animation with Stitching and Retargeting Control
Paper โข 2407.03168 โข Published โข 2Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/181465871908039 ๐ค Demo: https://huggingface.co/spaces/KwaiVGI/LivePortrait ๐ Paper: https://huggingface.co/papers/2407.03168 ๐ Github Page: https://liveportrait.github.io/ ๐ Repository: https://github.com/KwaiVGI/LivePortrait ๐ฅ Model ๐ค: https://huggingface.co/KwaiVGI/LivePortrait
A Simple Baseline for Spoken Language to Sign Language Translation with 3D Avatars
Paper โข 2401.04730 โข PublishedNote ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2401.04730 ๐ Repository: https://github.com/FangyunWei/SLRT
PICA: Physics-Integrated Clothed Avatar
Paper โข 2407.05324 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2407.05324 ๐ Github Page: https://ustc3dv.github.io/PICA/
MobilePortrait: Real-Time One-Shot Neural Head Avatars on Mobile Devices
Paper โข 2407.05712 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2407.05712 ๐ Github Page: https://mobileportrait.github.io/
RodinHD: High-Fidelity 3D Avatar Generation with Diffusion Models
Paper โข 2407.06938 โข Published โข 23Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/124284908420927 ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.06938 ๐ Github Page: https://rodinhd.github.io/ ๐ Repository: https://github.com/RodinHD/RodinHD ๐บ Video: https://www.youtube.com/watch?v=ULvHt7dZx-Q
IntrinsicAvatar: Physically Based Inverse Rendering of Dynamic Humans from Monocular Videos via Explicit Ray Tracing
Paper โข 2312.05210 โข PublishedNote ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/211717085209386 ๐ Conference: CVPR, Jun 17-21, 2024 | Seattle WA, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2312.05210 ๐ Github Page: https://neuralbodies.github.io/IntrinsicAvatar/ ๐ Repository: https://github.com/taconite/IntrinsicAvatar ๐บ Video: https://www.youtube.com/watch?v=aS8AIxgVXzI
MIGS: Multi-Identity Gaussian Splatting via Tensor Decomposition
Paper โข 2407.07284 โข PublishedNote ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.07284 ๐ Github Page: https://aggelinacha.github.io/MIGS ๐บ Video: https://www.youtube.com/watch?v=yUhIi3g5chI
WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation
Paper โข 2407.02165 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2407.02165 ๐ Github Page: https://wildavatar.github.io ๐ Repository: https://github.com/wildavatar/WildAvatar_Toolbox ๐บ Video: https://www.youtube.com/watch?v=T-XafMVKY7E
MeshAvatar: Learning High-quality Triangular Human Avatars from Multi-view Videos
Paper โข 2407.08414 โข PublishedNote ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/644671729298990 ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.08414 ๐ Github Page: https://shad0wta9.github.io/meshavatar-page ๐ Repository: https://github.com/shad0wta9/meshavatar ๐บ Video: https://www.youtube.com/watch?v=Kpbpujkh2iI
Tri^{2}-plane: Thinking Head Avatar via Feature Pyramid
Paper โข 2401.09386 โข PublishedNote ๐ Paper: https://huggingface.co/papers/2401.09386 ๐ Github Page: https://songluchuan.github.io/Tri2Plane.github.io ๐ Repository: https://github.com/Songluchuan/Tri2plane ๐บ Video: https://www.youtube.com/watch?v=qU7zijI2DCQ
CanonicalFusion: Generating Drivable 3D Human Avatars from Multiple Images
Paper โข 2407.04345 โข PublishedNote ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.04345 ๐ Repository: https://github.com/jsshin98/CanonicalFusion
iHuman: Instant Animatable Digital Humans From Monocular Videos
Paper โข 2407.11174 โข PublishedNote ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.11174 ๐ Github Page: https://pramishp.github.io/iHuman/index.html ๐ Repository: https://github.com/pramishp/ihuman ๐บ Video: https://www.youtube.com/watch?v=W5xG2GYfUM0
EmoFace: Audio-driven Emotional 3D Face Animation
Paper โข 2407.12501 โข PublishedNote ๐ Conference: VR, March 16-21, 2024 | Orlando FL, USA ๐บ๐ธ ๐ Paper: https://huggingface.co/papers/2407.12501 ๐ Github Page: https://sjtu-lucy.github.io/EmoFace ๐ Repository: https://github.com/SJTU-Lucy/EmoFace
HIMO: A New Benchmark for Full-Body Human Interacting with Multiple Objects
Paper โข 2407.12371 โข PublishedNote ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.12371 ๐ Github Page: https://lvxintao.github.io/himo ๐ Repository: https://github.com/LvXinTao/HIMO_dataset
Fast Registration of Photorealistic Avatars for VR Facial Animation
Paper โข 2401.11002 โข Published โข 2Note ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2401.11002 ๐ Github Page: https://chaitanya100100.github.io/FastRegistration ๐ Repository: https://github.com/chaitanya100100/FastRegistration ๐บ Video: https://www.youtube.com/watch?v=Jq_KJV3QoJ0
Expressive Whole-Body 3D Gaussian Avatar
Paper โข 2407.21686 โข Published โข 7Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/144143912433557 ๐ Conference: ECCV, 29 Sep โ 4 Oct, 2024 | Milano, Italy ๐ฎ๐น ๐ Paper: https://huggingface.co/papers/2407.21686 ๐ Github Page: https://mks0601.github.io/ExAvatar ๐ Repository: https://github.com/mks0601/ExAvatar_RELEASE
HeadGAP: Few-shot 3D Head Avatar via Generalizable Gaussian Priors
Paper โข 2408.06019 โข Published โข 13Note ๐ฎ Post: https://huggingface.co/posts/DmitryRyumin/334746128110541 ๐ Paper: https://huggingface.co/papers/2408.06019 ๐ Github Page: https://headgap.github.io
Loopy: Taming Audio-Driven Portrait Avatar with Long-Term Motion Dependency
Paper โข 2409.02634 โข Published โข 90Note ๐ Paper: https://huggingface.co/papers/2409.02634 ๐ Github Page: https://loopyavatar.github.io
Instant Facial Gaussians Translator for Relightable and Interactable Facial Rendering
Paper โข 2409.07441 โข Published โข 10Note ๐ Paper: https://huggingface.co/papers/2409.07441 ๐ Github Page: https://dafei-qin.github.io/TransGS.github.io ๐บ Video: https://www.youtube.com/watch?v=MQTm3WTQ3KI
Portrait Video Editing Empowered by Multimodal Generative Priors
Paper โข 2409.13591 โข Published โข 16Note ๐ Conference: SIGGRAPH Asia, Dec 3-6, 2024 | Tokyo, Japan ๐ฏ๐ต ๐ Paper: https://huggingface.co/papers/2409.13591 ๐ Github Page: https://ustc3dv.github.io/PortraitGen ๐ Repository: https://github.com/USTC3DV/PortraitGen-code
HeadGaS: Real-Time Animatable Head Avatars via 3D Gaussian Splatting
Paper โข 2312.02902 โข PublishedTextToon: Real-Time Text Toonify Head Avatar from Single Video
Paper โข 2410.07160 โข Published โข 8DAWN: Dynamic Frame Avatar with Non-autoregressive Diffusion Framework for Talking Head Video Generation
Paper โข 2410.13726 โข Published โข 11IDOL: Instant Photorealistic 3D Human Creation from a Single Image
Paper โข 2412.14963 โข Published โข 5