Librarian Bot. I found the following papers similar to this paper.

The following papers were recommended by the Semantic Scholar API

AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text (2023)
Animatable Gaussians: Learning Pose-dependent Gaussian Maps for High-fidelity Human Avatar Modeling (2023)
Human Gaussian Splatting: Real-time Rendering of Animatable Avatars (2023)
Gaussian Head Avatar: Ultra High-fidelity Head Avatar via Dynamic Gaussians (2023)
GaussianAvatar: Towards Realistic Human Avatar Modeling from a Single Video via Animatable 3D Gaussians (2023)

Please give a thumbs up to this comment if you found it helpful!

If you want recommendations for any Paper on Hugging Face checkout this Space

\n","updatedAt":"2023-12-21T14:46:46.633Z","author":{"_id":"63d3e0e8ff1384ce6c5dd17d","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg","fullname":"Librarian Bot (Bot)","name":"librarian-bot","type":"user","isPro":false,"isHf":false,"isHfAdmin":false,"isMod":false,"followerCount":318,"isUserFollowing":false}},"numEdits":0,"identifiedLanguage":{"language":"en","probability":0.7077834010124207},"editors":["librarian-bot"],"editorAvatarUrls":["https://cdn-avatars.huggingface.co/v1/production/uploads/1674830754237-63d3e0e8ff1384ce6c5dd17d.jpeg"],"reactions":[],"isReport":false}}],"primaryEmailConfirmed":false,"paper":{"id":"2312.11461","authors":[{"_id":"6581359b8108945fd3c61654","name":"Ye Yuan","hidden":false},{"_id":"6581359b8108945fd3c61655","user":{"_id":"6263685063f73be3d2f97604","avatarUrl":"/avatars/9c5d2f81cfd84bc835e4feb11b5e60b3.svg","isPro":false,"fullname":"Xueting Li","user":"sunshineatnoon","type":"user"},"name":"Xueting Li","status":"admin_assigned","statusLastChangedAt":"2023-12-19T09:30:02.457Z","hidden":false},{"_id":"6581359b8108945fd3c61656","user":{"_id":"630461923926de1f7ec7a93a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/no-auth/GoUU2qRfLB2wlcciwVBrz.png","isPro":false,"fullname":"Yangyi, Huang","user":"YangyiH","type":"user"},"name":"Yangyi Huang","status":"claimed_verified","statusLastChangedAt":"2025-09-08T07:04:29.484Z","hidden":false},{"_id":"6581359b8108945fd3c61657","user":{"_id":"623f6ac3f1c25923c98a892a","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1648323201428-noauth.png","isPro":false,"fullname":"Shalini De Mello","user":"shalinidemello","type":"user"},"name":"Shalini De Mello","status":"admin_assigned","statusLastChangedAt":"2023-12-19T09:30:24.424Z","hidden":false},{"_id":"6581359b8108945fd3c61658","user":{"_id":"637eb1c71dbae09191059243","avatarUrl":"/avatars/674b1a6e419c758a8613338d20f21544.svg","isPro":false,"fullname":"Koki Nagano","user":"luminohope","type":"user"},"name":"Koki Nagano","status":"admin_assigned","statusLastChangedAt":"2023-12-19T09:30:32.186Z","hidden":false},{"_id":"6581359b8108945fd3c61659","name":"Jan Kautz","hidden":false},{"_id":"6581359b8108945fd3c6165a","name":"Umar Iqbal","hidden":false}],"publishedAt":"2023-12-18T18:59:12.000Z","submittedOnDailyAt":"2023-12-19T03:48:07.438Z","title":"GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning","submittedOnDailyBy":{"_id":"60f1abe7544c2adfd699860c","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/1674929746905-60f1abe7544c2adfd699860c.jpeg","isPro":false,"fullname":"AK","user":"akhaliq","type":"user"},"summary":"Gaussian splatting has emerged as a powerful 3D representation that harnesses\nthe advantages of both explicit (mesh) and implicit (NeRF) 3D representations.\nIn this paper, we seek to leverage Gaussian splatting to generate realistic\nanimatable avatars from textual descriptions, addressing the limitations (e.g.,\nflexibility and efficiency) imposed by mesh or NeRF-based representations.\nHowever, a naive application of Gaussian splatting cannot generate high-quality\nanimatable avatars and suffers from learning instability; it also cannot\ncapture fine avatar geometries and often leads to degenerate body parts. To\ntackle these problems, we first propose a primitive-based 3D Gaussian\nrepresentation where Gaussians are defined inside pose-driven primitives to\nfacilitate animation. Second, to stabilize and amortize the learning of\nmillions of Gaussians, we propose to use neural implicit fields to predict the\nGaussian attributes (e.g., colors). Finally, to capture fine avatar geometries\nand extract detailed meshes, we propose a novel SDF-based implicit mesh\nlearning approach for 3D Gaussians that regularizes the underlying geometries\nand extracts highly detailed textured meshes. Our proposed method, GAvatar,\nenables the large-scale generation of diverse animatable avatars using only\ntext prompts. GAvatar significantly surpasses existing methods in terms of both\nappearance and geometry quality, and achieves extremely fast rendering (100\nfps) at 1K resolution.","upvotes":19,"discussionId":"6581359f8108945fd3c61737","ai_summary":"A method combining Gaussian splatting with neural implicit fields and SDF-based mesh learning for generating realistic and animatable avatars from text prompts, achieving high-quality appearance and geometry with fast rendering.","ai_keywords":["Gaussian splatting","explicit representations","implicit representations","NeRF","primitive-based 3D Gaussian representation","neural implicit fields","SDF-based mesh learning","appearance quality","geometry quality","fast rendering"]},"canReadDatabase":false,"canManagePapers":false,"canSubmit":false,"hasHfLevelAccess":false,"upvoted":false,"upvoters":[{"_id":"6538119803519fddb4a17e10","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6538119803519fddb4a17e10/ffJMkdx-rM7VvLTCM6ri_.jpeg","isPro":false,"fullname":"samusenps","user":"samusenps","type":"user"},{"_id":"6549135c196ae037a74e10a3","avatarUrl":"/avatars/86194456844c7b2b5389de36cb258472.svg","isPro":false,"fullname":"Richrich","user":"RichardForests","type":"user"},{"_id":"646d0c1c534e52f8c30500a6","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/646d0c1c534e52f8c30500a6/75VH8ClbRaP75BU2ONfXE.png","isPro":true,"fullname":"Pavlo Molchanov","user":"pmolchanov","type":"user"},{"_id":"65025370b6595dc45c397340","avatarUrl":"/avatars/9469599b176034548042922c0afa7051.svg","isPro":false,"fullname":"J C","user":"dark-pen","type":"user"},{"_id":"64cc87e471b435a75de026f1","avatarUrl":"/avatars/6fc1a2505d18576a1933633c4b13d805.svg","isPro":false,"fullname":"xuyangcao","user":"newxuyangcao","type":"user"},{"_id":"61b4807765b436cd727d24dc","avatarUrl":"/avatars/8e99539678634f4480b5eced06aa5c0e.svg","isPro":false,"fullname":"kilik","user":"kilik","type":"user"},{"_id":"60c8d264224e250fb0178f77","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/60c8d264224e250fb0178f77/i8fbkBVcoFeJRmkQ9kYAE.png","isPro":false,"fullname":"Adam Lee","user":"Abecid","type":"user"},{"_id":"6141a88b3a0ec78603c9e784","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/6141a88b3a0ec78603c9e784/DJsxSmWV39M33JFheLobC.jpeg","isPro":true,"fullname":"merve","user":"merve","type":"user"},{"_id":"633643ad9895307563630703","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/633643ad9895307563630703/XqfNJclu1dyITtThTrBD2.png","isPro":false,"fullname":"cesarkon","user":"adbrasi","type":"user"},{"_id":"63d4c8ce13ae45b780792f32","avatarUrl":"https://cdn-avatars.huggingface.co/v1/production/uploads/63d4c8ce13ae45b780792f32/QasegimoxBqfZwDzorukz.png","isPro":false,"fullname":"Ohenenoo","user":"PeepDaSlan9","type":"user"},{"_id":"6344bcd4cbc4ea2ab7417eb8","avatarUrl":"/avatars/3b4d7ecc3089e6352d2d80e76a738bed.svg","isPro":false,"fullname":"Salvador Salcedo","user":"ssalcedo00","type":"user"},{"_id":"648eb1eb59c4e5c87dc116e0","avatarUrl":"/avatars/c636cea39c2c0937f01398c94ead5dad.svg","isPro":false,"fullname":"fdsqefsgergd","user":"T-representer","type":"user"}],"acceptLanguages":["*"],"dailyPaperRank":0}">

Papers

arxiv:2312.11461

GAvatar: Animatable 3D Gaussian Avatars with Implicit Mesh Learning

Published on Dec 18, 2023

· Submitted by

AK on Dec 19, 2023

Upvote

Authors:

Xueting Li ,

Yangyi Huang ,

Shalini De Mello ,

Koki Nagano ,

Abstract

A method combining Gaussian splatting with neural implicit fields and SDF-based mesh learning for generating realistic and animatable avatars from text prompts, achieving high-quality appearance and geometry with fast rendering.

AI-generated summary

Gaussian splatting has emerged as a powerful 3D representation that harnesses the advantages of both explicit (mesh) and implicit (NeRF) 3D representations. In this paper, we seek to leverage Gaussian splatting to generate realistic animatable avatars from textual descriptions, addressing the limitations (e.g., flexibility and efficiency) imposed by mesh or NeRF-based representations. However, a naive application of Gaussian splatting cannot generate high-quality animatable avatars and suffers from learning instability; it also cannot capture fine avatar geometries and often leads to degenerate body parts. To tackle these problems, we first propose a primitive-based 3D Gaussian representation where Gaussians are defined inside pose-driven primitives to facilitate animation. Second, to stabilize and amortize the learning of millions of Gaussians, we propose to use neural implicit fields to predict the Gaussian attributes (e.g., colors). Finally, to capture fine avatar geometries and extract detailed meshes, we propose a novel SDF-based implicit mesh learning approach for 3D Gaussians that regularizes the underlying geometries and extracts highly detailed textured meshes. Our proposed method, GAvatar, enables the large-scale generation of diverse animatable avatars using only text prompts. GAvatar significantly surpasses existing methods in terms of both appearance and geometry quality, and achieves extremely fast rendering (100 fps) at 1K resolution.