Locally Aware Piecewise Transformation Fields for 3D Human Mesh Registration
Registering point clouds of dressed humans to parametric human models is a challenging task in computer vision. Traditional approaches often rely on heavily engineered pipelines that require accurate manual initialization of human poses and tedious post-processing. More recently, learning-based methods are proposed in hope to automate this process. We observe that pose initialization is key to accurate registration but existing methods often fail to provide accurate pose initialization. One major obstacle is that, regressing joint rotations from point clouds or images of humans is still very challenging. To this end, we propose novel piecewise transformation fields (PTF), a set of functions that learn 3D translation vectors to map any query point in posed space to its correspond position in rest-pose space. We combine PTF with multi-class occupancy networks, obtaining a novel learning-based framework that learns to simultaneously predict shape and per-point correspondences between the posed space and the canonical space for clothed human. Our key insight is that the translation vector for each query point can be effectively estimated using the point-aligned local features; consequently, rigid per bone transformations and joint rotations can be obtained efficiently via a least-square fitting given the estimated point correspondences, circumventing the challenging task of directly regressing joint rotations from neural networks. Furthermore, the proposed PTF facilitate canonicalized occupancy estimation, which greatly improves generalization capability and results in more accurate surface reconstruction with only half of the parameters compared with the state-of-the-art. Both qualitative and quantitative studies show that fitting parametric models with poses initialized by our network results in much better registration quality, especially for extreme poses.
Code (0)
등록된 구현이 없습니다.
Tasks
Surface ReconstructionTranslationSimilar Papers 제목 키워드 기반
Highly-Expressive Spaces of Well-Behaved Transformations: Keeping It Simple
We propose novel finite-dimensional spaces of R - R transformations, n [?] 1, 2, 3, derived from (continuously-defined) parametric stationary velocity fields. Particularly, we obtain these transformations, which are diff…
Image RegistrationDeepFace: Closing the Gap to Human-Level Performance in Face Verification
In modern face recognition, the conventional pipeline consists of four stages: detect => align => represent => classify. We revisit both the alignment step and the representation step by employing explicit 3D face modeli…
3D Face ModellingFace RecognitionFace VerificationPARN: Pyramidal Affine Regression Networks for Dense Semantic Correspondence
This paper presents a deep architecture for dense semantic correspondence, called pyramidal affine regression networks (PARN), that estimates locally-varying affine transformation fields across images. To deal with intra…
regressionSemantic correspondenceMetaMorph: Learning Metamorphic Image Transformation With Appearance Changes
This paper presents a novel predictive model, MetaMorph, for metamorphic registration of images with appearance changes (i.e., caused by brain tumors). In contrast to previous learning-based registration methods that hav…
SegmentationLocally Linear Continual Learning for Time Series based on VC-Theoretical Generalization Bounds
Most machine learning methods assume fixed probability distributions, limiting their applicability in nonstationary real-world scenarios. While continual learning methods address this issue, current approaches often rely…
Time Series ForecastingContinual Learning