LOHO: Latent Optimization of Hairstyles via Orthogonalization

• URL: http://arxiv.org/abs/2103.03891v1
• Date: Fri, 5 Mar 2021 19:00:33 GMT
• Title: LOHO: Latent Optimization of Hairstyles via Orthogonalization
• Authors: Rohit Saha and Brendan Duke and Florian Shkurti and Graham W. Taylor and Parham Aarabi
• Abstract summary: We propose an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer. Our approach decomposes hair into three attributes: perceptual structure, appearance, and style, and includes tailored losses to model each of these attributes independently.
• Score: 20.18175263304822
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Hairstyle transfer is challenging due to hair structure differences in the source and target hair. Therefore, we propose Latent Optimization of Hairstyles via Orthogonalization (LOHO), an optimization-based approach using GAN inversion to infill missing hair structure details in latent space during hairstyle transfer. Our approach decomposes hair into three attributes: perceptual structure, appearance, and style, and includes tailored losses to model each of these attributes independently. Furthermore, we propose two-stage optimization and gradient orthogonalization to enable disentangled latent space optimization of our hair attributes. Using LOHO for latent space manipulation, users can synthesize novel photorealistic images by manipulating hair attributes either individually or jointly, transferring the desired attributes from reference hairstyles. LOHO achieves a superior FID compared with the current state-of-the-art (SOTA) for hairstyle transfer. Additionally, LOHO preserves the subject's identity comparably well according to PSNR and SSIM when compared to SOTA image embedding pipelines.

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)
• HairFastGAN: Realistic and Robust Hair Transfer with a Fast Encoder-Based Approach [3.737361598712633]
  We present the HairFast model, which achieves high resolution, near real-time performance, and superior reconstruction. Our solution includes a new architecture operating in the FS latent space of StyleGAN. In the most difficult scenario of transferring both shape and color of a hairstyle from different images, our method performs in less than a second on the Nvidia V100.
  arXiv  Detail & Related papers  (2024-04-01T12:59:49Z)
• 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)
• Anti-Aliased Neural Implicit Surfaces with Encoding Level of Detail [54.03399077258403]
  We present LoD-NeuS, an efficient neural representation for high-frequency geometry detail recovery and anti-aliased novel view rendering. Our representation aggregates space features from a multi-convolved featurization within a conical frustum along a ray.
  arXiv  Detail & Related papers  (2023-09-19T05:44:00Z)
• Generalizable One-shot Neural Head Avatar [90.50492165284724]
  We present a method that reconstructs and animates a 3D head avatar from a single-view portrait image. We propose a framework that not only generalizes to unseen identities based on a single-view image, but also captures characteristic details within and beyond the face area.
  arXiv  Detail & Related papers  (2023-06-14T22:33:09Z)
• Neural Haircut: Prior-Guided Strand-Based Hair Reconstruction [4.714310894654027]
  This work proposes an approach capable of accurate hair geometry reconstruction at a strand level from a monocular video or multi-view images captured in uncontrolled conditions. The combined system, named Neural Haircut, achieves high realism and personalization of the reconstructed hairstyles.
  arXiv  Detail & Related papers  (2023-06-09T13:08:34Z)
• Deep Diversity-Enhanced Feature Representation of Hyperspectral Images [87.47202258194719]
  We rectify 3D convolution by modifying its topology to enhance the rank upper-bound. We also propose a novel diversity-aware regularization (DA-Reg) term that acts on the feature maps to maximize independence among elements. To demonstrate the superiority of the proposed Re$3$-ConvSet and DA-Reg, we apply them to various HS image processing and analysis tasks.
  arXiv  Detail & Related papers  (2023-01-15T16:19:18Z)
• Efficient Hair Style Transfer with Generative Adversarial Networks [7.312180925669325]
  We propose a novel hairstyle transfer method, called EHGAN, which reduces computational costs to enable real-time processing. To achieve this goal, we train an encoder and a low-resolution generator to transfer hairstyle and then, increase the resolution of results with a pre-trained super-resolution model. EHGAN needs around 2.7 times and over 10,000 times less time consumption than the state-of-the-art MichiGAN and LOHO methods respectively.
  arXiv  Detail & Related papers  (2022-10-22T18:56:16Z)
• Style Your Hair: Latent Optimization for Pose-Invariant Hairstyle Transfer via Local-Style-Aware Hair Alignment [29.782276472922398]
  We propose a pose-invariant hairstyle transfer model equipped with latent optimization and a newly presented local-style-matching loss. Our model has strengths in transferring a hairstyle under larger pose differences and preserving local hairstyle textures.
  arXiv  Detail & Related papers  (2022-08-16T14:23:54Z)
• High-resolution Face Swapping via Latent Semantics Disentanglement [50.23624681222619]
  We present a novel high-resolution hallucination face swapping method using the inherent prior knowledge of a pre-trained GAN model. We explicitly disentangle the latent semantics by utilizing the progressive nature of the generator. We extend our method to video face swapping by enforcing two-temporal constraints on the latent space and the image space.
  arXiv  Detail & Related papers  (2022-03-30T00:33:08Z)
• MichiGAN: Multi-Input-Conditioned Hair Image Generation for Portrait Editing [122.82964863607938]
  MichiGAN is a novel conditional image generation method for interactive portrait hair manipulation. We provide user control over every major hair visual factor, including shape, structure, appearance, and background. We also build an interactive portrait hair editing system that enables straightforward manipulation of hair by projecting intuitive and high-level user inputs.
  arXiv  Detail & Related papers  (2020-10-30T17:59:10Z)

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.