FARM: Functional Automatic Registration Method for 3D Human Bodies

Marin, Riccardo; Melzi, Simone; Rodolà, Emanuele; Castellani, Umberto

doi:10.1111/cgf.13751

Cited by 48 publications

(48 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Most closely related to this paper are the works [50] and [24]. Both works build upon the general idea of a deformation-driven approach for shape matching.…”

Section: Related Workmentioning

confidence: 99%

“…Both works build upon the general idea of a deformation-driven approach for shape matching. In particular, the FARM method [24] produces a high-quality correspondence through an iterative deformation of a given parametric model (the authors adopt the SMPL [20] morphable model) into a given target shape. The approach relies on a spectral matching step based on the functional maps representation.…”

Section: Related Workmentioning

confidence: 99%

“…However, due to their band-limited representation, such approaches often suffer from poor point-wise resolution especially in areas of high geometric detail. To face this limitation, Marin et al [24] proposed to combine the benefits of a 3D Morphable Model with those of functional maps, thereby unifying the intrinsic description of a surface with a strong extrinsic regularization. By doing so, the authors showed significant improvement over prior work in several challenging cases.…”

Section: Introductionmentioning

confidence: 99%

“…Despite these advantages, the approach of [24] can not go beyond the resolution of the underlying parametric model, which can be a significant limiting factor whenever retaining the full resolution of the target shape is a strong requirement. In this paper we propose a method to increase the resolution of the registered template, thus overcoming a key limitation of existing approaches as shown on a real example in Fig.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

Marin

Melzi

Rodolà

et al. 2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

We propose a new approach for 3D shape matching of deformable human shapes. Our approach is based on the joint adoption of three different tools: an intrinsic spectral matching pipeline, a morphable model, and an extrinsic details refinement. By operating in conjunction, these tools allow us to greatly improve the quality of the matching while at the same time resolving the key issues exhibited by each tool individually. In this paper we present an innovative High-Resolution Augmentation (HRA) strategy that enables highly accurate correspondence even in the presence of significant mesh resolution mismatch between the input shapes. This augmentation provides an effective workaround for the resolution limitations imposed by the adopted morphable model. The HRA in its global and localized versions represents a novel refinement strategy for surface subdivision methods. We demonstrate the accuracy of the proposed pipeline on multiple challenging benchmarks, and showcase its effectiveness in surface registration and texture transfer.

show abstract

“…Most closely related to this paper are the works [50] and [24]. Both works build upon the general idea of a deformation-driven approach for shape matching.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

High-Resolution Augmentation for Automatic Template-Based Matching of Human Models

Marin

Melzi

Rodolà

et al. 2019

2019 International Conference on 3D Vision (3DV)

View full text Add to dashboard Cite

show abstract

“…SHREC19 [Melzi et al 2019] is a recent benchmark composed of 430 human pairs with different connectivity and mesh resolution, gathered using 44 different shapes from 11 datasets. Each shape is aligned to the SMPL model [Loper et al 2015] using the registration pipeline of [Marin et al 2018], thus providing a dense ground truth for quantitative evaluation. This benchmark is challenging due to high shape variance and due to the presence of high-resolution meshes (5K to 200K vertices, see supplementary materials for examples).…”

Section: 23mentioning

confidence: 99%

ZoomOut

et al. 2019

View full text Add to dashboard Cite

We present a simple and efficient method for refining maps or correspondences by iterative upsampling in the spectral domain that can be implemented in a few lines of code. Our main observation is that high quality maps can be obtained even if the input correspondences are noisy or are encoded by a small number of coefficients in a spectral basis. We show how this approach can be used in conjunction with existing initialization techniques across a range of application scenarios, including symmetry detection, map refinement across complete shapes, non-rigid partial shape matching and function transfer. In each application we demonstrate an improvement with respect to both the quality of the results and the computational speed compared to the best competing methods, with up to two orders of magnitude speed-up in some applications. We also demonstrate that our method is both robust to noisy input and is scalable with respect to shape complexity. Finally, we present a theoretical justification for our approach, shedding light on structural properties of functional maps.155:2 • Melzi. et al the same or better quality at a fraction of the cost compared to the current top performing methods.(2) We demonstrate how higher-frequency information can be extracted from low-frequency spectral map representations. (3) We introduce a novel variational optimization problem and develop a theoretical justification of our method, shedding light on structural properties of functional maps. RELATED WORKShape matching is a very well-studied area of computer graphics. Below we review the methods most closely related to ours, concentrating on spectral techniques for finding correspondences between non-rigid shapes. We refer the interested readers to recent surveys including [Biasotti et al. 2016;Tam et al. 2013;Van Kaick et al. 2011] for a more in-depth treatment of the area.Point-based Spectral Methods. Early spectral methods for shape correspondence were based on directly optimizing pointwise maps between spectral shape embeddings based on either adjacency or Laplacian matrices of graphs and triangle meshes [Jain and Zhang 2006;Jain et al. 2007;Mateus et al. 2008;Ovsjanikov et al. 2010;Scott and Longuet-Higgins 1991;Umeyama 1988]. Such approaches suffer from the requirement of a good initialization, and rely on restricting assumptions about the type of transformation relating the shapes. An initialization algorithm with optimality guarantees, although limited to few tens of points, was introduced in [Maron et al. 2016] and later extended to deal with intrinsic symmetries in [Dym and Lipman 2017]. Spectral quantities (namely, sequences of Laplacian eigenfunctions) have also been used to define pointwise descriptors, and employed within variants of the quadratic assignment problem in Kimmel 2010, 2011]. These approaches have been recently generalized by spectral generalized multidimensional scaling [Aflalo et al. 2016], which explicitly formulates minimumdistortion shape correspondence in the spectral domain.

show abstract