DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models

• URL: http://arxiv.org/abs/2505.06166v1
• Date: Fri, 09 May 2025 16:16:42 GMT
• Title: DiffLocks: Generating 3D Hair from a Single Image using Diffusion Models
• Authors: Radu Alexandru Rosu, Keyu Wu, Yao Feng, Youyi Zheng, Michael J. Black,
• Abstract summary: We propose DiffLocks, a novel framework that enables reconstruction of a wide variety of hairstyles directly from a single image.<n>First, we address the lack of 3D hair data by automating the creation of the largest synthetic hair dataset to date, containing 40K hairstyles.<n>By using a pretrained image backbone, our method generalizes to in-the-wild images despite being trained only on synthetic data.
• Score: 53.08138861924767
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We address the task of generating 3D hair geometry from a single image, which is challenging due to the diversity of hairstyles and the lack of paired image-to-3D hair data. Previous methods are primarily trained on synthetic data and cope with the limited amount of such data by using low-dimensional intermediate representations, such as guide strands and scalp-level embeddings, that require post-processing to decode, upsample, and add realism. These approaches fail to reconstruct detailed hair, struggle with curly hair, or are limited to handling only a few hairstyles. To overcome these limitations, we propose DiffLocks, a novel framework that enables detailed reconstruction of a wide variety of hairstyles directly from a single image. First, we address the lack of 3D hair data by automating the creation of the largest synthetic hair dataset to date, containing 40K hairstyles. Second, we leverage the synthetic hair dataset to learn an image-conditioned diffusion-transfomer model that generates accurate 3D strands from a single frontal image. By using a pretrained image backbone, our method generalizes to in-the-wild images despite being trained only on synthetic data. Our diffusion model predicts a scalp texture map in which any point in the map contains the latent code for an individual hair strand. These codes are directly decoded to 3D strands without post-processing techniques. Representing individual strands, instead of guide strands, enables the transformer to model the detailed spatial structure of complex hairstyles. With this, DiffLocks can recover highly curled hair, like afro hairstyles, from a single image for the first time. Data and code is available at https://radualexandru.github.io/difflocks/

Related papers

• Towards Unified 3D Hair Reconstruction from Single-View Portraits [27.404011546957104]
  We propose a novel strategy to enable single-view 3D reconstruction for a variety of hair types via a unified pipeline. Our experiments demonstrate that reconstructing braided and un-braided 3D hair from single-view images via a unified approach is possible.
  arXiv  Detail & Related papers  (2024-09-25T12:21:31Z)
• Human Hair Reconstruction with Strand-Aligned 3D Gaussians [39.32397354314153]
  We introduce a new hair modeling method that uses a dual representation of classical hair strands and 3D Gaussians. In contrast to recent approaches that leverage unstructured Gaussians to model human avatars, our method reconstructs the hair using 3D polylines, or strands. Our method, named Gaussian Haircut, is evaluated on synthetic and real scenes and demonstrates state-of-the-art performance in the task of strand-based hair reconstruction.
  arXiv  Detail & Related papers  (2024-09-23T07:49:46Z)
• Perm: A Parametric Representation for Multi-Style 3D Hair Modeling [22.790597419351528]
  Perm is a learned parametric representation of human 3D hair designed to facilitate various hair-related applications.<n>We leverage our strand representation to fit and decompose hair geometry textures into low- to high-frequency hair structures.
  arXiv  Detail & Related papers  (2024-07-28T10:05:11Z)
• HAAR: Text-Conditioned Generative Model of 3D Strand-based Human Hairstyles [85.12672855502517]
  We present HAAR, a new strand-based generative model for 3D human hairstyles. Based on textual inputs, HAAR produces 3D hairstyles that could be used as production-level assets in modern computer graphics engines.
  arXiv  Detail & Related papers  (2023-12-18T19:19:32Z)
• 3DStyle-Diffusion: Pursuing Fine-grained Text-driven 3D Stylization with 2D Diffusion Models [102.75875255071246]
  3D content creation via text-driven stylization has played a fundamental challenge to multimedia and graphics community. We propose a new 3DStyle-Diffusion model that triggers fine-grained stylization of 3D meshes with additional controllable appearance and geometric guidance from 2D Diffusion models.
  arXiv  Detail & Related papers  (2023-11-09T15:51:27Z)
• HairStep: Transfer Synthetic to Real Using Strand and Depth Maps for Single-View 3D Hair Modeling [55.57803336895614]
  We tackle the challenging problem of learning-based single-view 3D hair modeling. We first propose a novel intermediate representation, termed as HairStep, which consists of a strand map and a depth map. It is found that HairStep not only provides sufficient information for accurate 3D hair modeling, but also is feasible to be inferred from real images.
  arXiv  Detail & Related papers  (2023-03-05T15:28:13Z)
• PeRFception: Perception using Radiance Fields [72.99583614735545]
  We create the first large-scale implicit representation datasets for perception tasks, called the PeRFception. It shows a significant memory compression rate (96.4%) from the original dataset, while containing both 2D and 3D information in a unified form. We construct the classification and segmentation models that directly take as input this implicit format and also propose a novel augmentation technique to avoid overfitting on backgrounds of images.
  arXiv  Detail & Related papers  (2022-08-24T13:32:46Z)
• i3DMM: Deep Implicit 3D Morphable Model of Human Heads [115.19943330455887]
  We present the first deep implicit 3D morphable model (i3DMM) of full heads. It not only captures identity-specific geometry, texture, and expressions of the frontal face, but also models the entire head, including hair. We show the merits of i3DMM using ablation studies, comparisons to state-of-the-art models, and applications such as semantic head editing and texture transfer.
  arXiv  Detail & Related papers  (2020-11-28T15:01:53Z)

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.