Static/Dynamic Filtering for Mesh Geometry

Abstract

The joint bilateral filter, which enables feature-preserving signal smoothing according to the structural information from a guidance, has been applied for various tasks in geometry processing. Existing methods either rely on a static guidance that may be inconsistent with the input and lead to unsatisfactory results, or a dynamic guidance that is automatically updated but sensitive to noises and outliers. Inspired by recent advances in image filtering, we propose a new geometry filtering technique called static/dynamic filter, which utilizes both static and dynamic guidances to achieve state-of-the-art results. The proposed filter is based on a nonlinear optimization that enforces smoothness of the signal while preserving variations that correspond to features of certain scales. We develop an efficient iterative solver for the problem, which unifies existing filters that are based on static or dynamic guidances. The filter can be applied to mesh face normals followed by vertex position update, to achieve scale-aware and feature-preserving filtering of mesh geometry. It also works well for other types of signals defined on mesh surfaces, such as texture colors. Extensive experimental results demonstrate the effectiveness of the proposed filter for various geometry processing applications such as mesh denoising, geometry feature enhancement, and texture color filtering.

Spatially Adaptive Regularizer for Mesh Denoising

“…As the facet normals might contain desirable anisotropic information of features and are well defined anywhere on a surface, many filter-based mesh denoising methods follow a two-stage scheme: firstly filter facet normals and then update vertex positions. There exits mean and median facet normal filter [21], alpha-trimming normal filter [22] and bilateral normal filter [7], [8], [23], [24].…”

“…The bilateral normal filter [7], [8], [23], [24] is a main class of filter-based mesh denoising methods. Zheng et al [7] extends the bilateral filter from the vertex position field [19], [20] to the facet normal field, and carefully define the spatial weight and range weight.…”

“…Another example is the rolling guidance filter [23], which iteratively uses the previous iterate as a dynamic guidance. More recently, Zhang et al [24] propose to combine static and dynamic guidance for more robust normal filtering, since the use of static vs dynamic guidance presents a trade-off between their properties.…”

A Deep Residual Network for Geometric Decontouring

“…The mesh smoothing techniques can be used to remove some false contours from a geometric point of view. These methods can be roughly categorized into two classes, including vertex based methods [FDCO03, JDD03, NISA06, LTJW07, HS13], and normal based methods [SRML07, ZFAT11, ZDZ*15, ZDH*18,LZFH18, YRP18]. The geometric quantities, such as vertices and normals, are taken into account, these methods seem better suited to the presented problem.…”

Reliable Rolling‐guided Point Normal Filtering for Surface Texture Removal

“…Moreover, they use the modified Possion‐based gradient deformation method to update mesh vertex positions. Furthermore, a new geometry filtering method named static/dynamic (SD) filter was presented by Zhang et al [ZDH*19] recently. The SD filter is also a variant of image processing [HCP15].…”