Pith. sign in

REVIEW 3 cited by

PBNS: Physically Based Neural Simulator for Unsupervised Garment Pose Space Deformation

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

arxiv 2012.11310 v3 pith:4O2CAXDQ submitted 2020-12-21 cs.CV cs.GR

classification cs.CVcs.GR
keywords learnspaceclothdatalearningmodelsphysicallypose
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

We present a methodology to automatically obtain Pose Space Deformation (PSD) basis for rigged garments through deep learning. Classical approaches rely on Physically Based Simulations (PBS) to animate clothes. These are general solutions that, given a sufficiently fine-grained discretization of space and time, can achieve highly realistic results. However, they are computationally expensive and any scene modification prompts the need of re-simulation. Linear Blend Skinning (LBS) with PSD offers a lightweight alternative to PBS, though, it needs huge volumes of data to learn proper PSD. We propose using deep learning, formulated as an implicit PBS, to unsupervisedly learn realistic cloth Pose Space Deformations in a constrained scenario: dressed humans. Furthermore, we show it is possible to train these models in an amount of time comparable to a PBS of a few sequences. To the best of our knowledge, we are the first to propose a neural simulator for cloth. While deep-based approaches in the domain are becoming a trend, these are data-hungry models. Moreover, authors often propose complex formulations to better learn wrinkles from PBS data. Supervised learning leads to physically inconsistent predictions that require collision solving to be used. Also, dependency on PBS data limits the scalability of these solutions, while their formulation hinders its applicability and compatibility. By proposing an unsupervised methodology to learn PSD for LBS models (3D animation standard), we overcome both of these drawbacks. Results obtained show cloth-consistency in the animated garments and meaningful pose-dependant folds and wrinkles. Our solution is extremely efficient, handles multiple layers of cloth, allows unsupervised outfit resizing and can be easily applied to any custom 3D avatar.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. SAFT: Shape and Appearance of Fabrics from Template via Differentiable Physical Simulations from Monocular Video

    cs.CV 2025-09 conditional novelty 6.0 of 10

    A physics-based shape-from-template method with two regularization terms reduces cloth reconstruction error by about 2.6x versus prior work and enables SVBRDF and lighting recovery from monocular video.

  2. HairFormer: Transformer-Based Dynamic Neural Hair Simulation

    cs.GR 2025-07 conditional novelty 6.0 of 10

    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.

  3. Self-supervised Learning of Latent Space Dynamics

    cs.GR 2025-07 conditional novelty 6.0 of 10

    A self-supervised neural integrator predicts elastic rod, shell, and solid dynamics entirely in latent space, enabling CPU real-time inference with stable long rollouts.

Pith tools