PuzzleAvatar: Assembling 3D Avatars from Personal Albums

• URL: http://arxiv.org/abs/2405.14869v2
• Date: Sat, 14 Sep 2024 19:08:50 GMT
• Title: PuzzleAvatar: Assembling 3D Avatars from Personal Albums
• Authors: Yuliang Xiu, Yufei Ye, Zhen Liu, Dimitrios Tzionas, Michael J. Black,
• Abstract summary: We develop PuzzleAvatar, a novel model that generates a faithful 3D avatar from a personal OOTD album. We exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar.
• Score: 54.831084076478874
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Generating personalized 3D avatars is crucial for AR/VR. However, recent text-to-3D methods that generate avatars for celebrities or fictional characters, struggle with everyday people. Methods for faithful reconstruction typically require full-body images in controlled settings. What if a user could just upload their personal "OOTD" (Outfit Of The Day) photo collection and get a faithful avatar in return? The challenge is that such casual photo collections contain diverse poses, challenging viewpoints, cropped views, and occlusion (albeit with a consistent outfit, accessories and hairstyle). We address this novel "Album2Human" task by developing PuzzleAvatar, a novel model that generates a faithful 3D avatar (in a canonical pose) from a personal OOTD album, while bypassing the challenging estimation of body and camera pose. To this end, we fine-tune a foundational vision-language model (VLM) on such photos, encoding the appearance, identity, garments, hairstyles, and accessories of a person into (separate) learned tokens and instilling these cues into the VLM. In effect, we exploit the learned tokens as "puzzle pieces" from which we assemble a faithful, personalized 3D avatar. Importantly, we can customize avatars by simply inter-changing tokens. As a benchmark for this new task, we collect a new dataset, called PuzzleIOI, with 41 subjects in a total of nearly 1K OOTD configurations, in challenging partial photos with paired ground-truth 3D bodies. Evaluation shows that PuzzleAvatar not only has high reconstruction accuracy, outperforming TeCH and MVDreamBooth, but also a unique scalability to album photos, and strong robustness. Our code and data are publicly available for research purpose at https://puzzleavatar.is.tue.mpg.de/

Related papers

• WildAvatar: Web-scale In-the-wild Video Dataset for 3D Avatar Creation [55.85887047136534]
  WildAvatar is a web-scale in-the-wild human avatar creation dataset extracted from YouTube. We evaluate several state-of-the-art avatar creation methods on our dataset, highlighting the unexplored challenges in real-world applications on avatar creation.
  arXiv  Detail & Related papers  (2024-07-02T11:17:48Z)
• Text2Avatar: Text to 3D Human Avatar Generation with Codebook-Driven Body Controllable Attribute [33.330629835556664]
  We propose Text2Avatar, which can generate realistic-style 3D avatars based on the coupled text prompts. To alleviate the scarcity of realistic style 3D human avatar data, we utilize a pre-trained unconditional 3D human avatar generation model.
  arXiv  Detail & Related papers  (2024-01-01T09:39:57Z)
• AvatarStudio: High-fidelity and Animatable 3D Avatar Creation from Text [71.09533176800707]
  AvatarStudio is a coarse-to-fine generative model that generates explicit textured 3D meshes for animatable human avatars. By effectively leveraging the synergy between the articulated mesh representation and the DensePose-conditional diffusion model, AvatarStudio can create high-quality avatars.
  arXiv  Detail & Related papers  (2023-11-29T18:59:32Z)
• AvatarVerse: High-quality & Stable 3D Avatar Creation from Text and Pose [23.76390935089982]
  We present AvatarVerse, a stable pipeline for generating high expressivequality 3D avatars from text descriptions and pose guidance. To this end, we propose zero-fidelity 3D modeling of 3D avatars that are not only more expressive, but also higher quality stablizes.
  arXiv  Detail & Related papers  (2023-08-07T14:09:46Z)
• AvatarBooth: High-Quality and Customizable 3D Human Avatar Generation [14.062402203105712]
  AvatarBooth is a novel method for generating high-quality 3D avatars using text prompts or specific images. Our key contribution is the precise avatar generation control by using dual fine-tuned diffusion models. We present a multi-resolution rendering strategy that facilitates coarse-to-fine supervision of 3D avatar generation.
  arXiv  Detail & Related papers  (2023-06-16T14:18:51Z)
• DreamWaltz: Make a Scene with Complex 3D Animatable Avatars [68.49935994384047]
  We present DreamWaltz, a novel framework for generating and animating complex 3D avatars given text guidance and parametric human body prior. For animation, our method learns an animatable 3D avatar representation from abundant image priors of diffusion model conditioned on various poses.
  arXiv  Detail & Related papers  (2023-05-21T17:59:39Z)
• OTAvatar: One-shot Talking Face Avatar with Controllable Tri-plane Rendering [81.55960827071661]
  Controllability, generalizability and efficiency are the major objectives of constructing face avatars represented by neural implicit field. We propose One-shot Talking face Avatar (OTAvatar), which constructs face avatars by a generalized controllable tri-plane rendering solution.
  arXiv  Detail & Related papers  (2023-03-26T09:12:03Z)
• MVP-Human Dataset for 3D Human Avatar Reconstruction from Unconstrained Frames [59.37430649840777]
  We present 3D Avatar Reconstruction in the wild (ARwild), which first reconstructs the implicit skinning fields in a multi-level manner. We contribute a large-scale dataset, MVP-Human, which contains 400 subjects, each of which has 15 scans in different poses. Overall, benefits from the specific network architecture and the diverse data, the trained model enables 3D avatar reconstruction from unconstrained frames.
  arXiv  Detail & Related papers  (2022-04-24T03:57:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.