REVIEW 4 cited by
Perm: A Parametric Representation for Multi-Style 3D Hair Modeling
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We present Perm, a learned parametric representation of human 3D hair designed to facilitate various hair-related applications. Unlike previous work that jointly models the global hair structure and local curl patterns, we propose to disentangle them using a PCA-based strand representation in the frequency domain, thereby allowing more precise editing and output control. Specifically, we leverage our strand representation to fit and decompose hair geometry textures into low- to high-frequency hair structures, termed guide textures and residual textures, respectively. These decomposed textures are later parameterized with different generative models, emulating common stages in the hair grooming process. We conduct extensive experiments to validate the architecture design of Perm, and finally deploy the trained model as a generic prior to solve task-agnostic problems, further showcasing its flexibility and superiority in tasks such as single-view hair reconstruction, hairstyle editing, and hair-conditioned image generation. More details can be found on our project page: https://cs.yale.edu/homes/che/projects/perm/.
Forward citations
Cited by 4 Pith papers
-
Detangled: A Framework for Creating, Editing, and Inferencing Feature Rich Hair Strands
A 5D texture parameterization plus centerline-based canonical space and supervised diffusion enables generation and texture transfer of feature-rich hair strands independent of style.
-
StrandDesigner: Towards Practical Strand Generation with Sketch Guidance
Sketch drawings can directly control 3D hair strand generation through multi-scale latent upsampling with adaptive DINOv2 conditioning, yielding more accurate results than text- or image-guided baselines.
-
HairFormer: Transformer-Based Dynamic Neural Hair Simulation
A transformer-based two-stage network predicts static hair drapes and dynamic hair motion for arbitrary hairstyles and body poses in real time, trained with physics-inspired losses rather than pre-simulated data.
-
TANGLED: Generating 3D Hair Strands from Images with Arbitrary Styles and Viewpoints
A lineart-conditioned multi-view diffusion model generates 3D hair strands from arbitrary style images, supported by a new 457-hairstyle dataset and braid inpainting.
Discussion (0). Continue with ORCID to comment.