Topology-Change-Aware Volumetric Fusion for Dynamic Scene Reconstruction

Li, Chao; Guo, Xiaohu

doi:10.1007/978-3-030-58517-4_16

Cited by 9 publications

(8 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Positional constraints Depending on the application, some points on the deformed surface are required to be close to some target positions. For example, when aligning a template mesh for human bodies or heads to scanned data, the landmark vertices on the deformed template mesh are required to be close to the landmark locations on the data [ACP03, SCO04, ARV07, YLSL10, TT16, LG20, ZFA21]. Such positional constraints can be enforced with the following term:…”

Section: Extrinsic Methodsmentioning

confidence: 99%

“…Since local rigidity implies that the distance metric is also preserved locally, some methods enforce the condition by penalizing the change of distance between each point and its neighboring points [WJH* 07, SWG08, IZN* 16, YGL* 19, LG20]:…”

Section: Extrinsic Methodsmentioning

confidence: 99%

“…Besides the 3D geometry itself, auxiliary information can also be used to identify initial correspondence. For example, for input surfaces in RGB‐D format, some methods first use compute SIFT features [Low04, LZW*09, IZN*16, LG20, ZFA21] on the RGB images to identify corresponding pixels; the correspondence is then transferred to the 3D surfaces using the association between the RGB and the depth data [ZST*10,MQZ*15,IZN*16].…”

Section: Extrinsic Methodsmentioning

confidence: 99%

“…The point‐to‐plane distance has been used in many non‐rigid registration algorithms [LAGP09, XLC*18, LYP*20]. It can be used either as the alignment term alone [DKD* 16, YGX* 17, DDF* 17, LZG18, YZG* 18, ZBYX19, LYP*20,LZXH20], or in combination with the point‐to‐point distance in (8) [LAGP09, CZ11, YKM13, AZB15, GXW* 15, TT16, IZN*16,LJY*17,WZX17,XLC*18,LG20, SXZ*20,ZFA21].…”

Section: Extrinsic Methodsmentioning

confidence: 99%

See 3 more Smart Citations

A Survey of Non‐Rigid 3D Registration

Deng

Yao

Dyke

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

Non-rigid registration computes an alignment between a source surface with a target surface in a non-rigid manner. In the past decade, with the advances in 3D sensing technologies that can measure time-varying surfaces, non-rigid registration has been applied for the acquisition of deformable shapes and has a wide range of applications. This survey presents a comprehensive review of non-rigid registration methods for 3D shapes, focusing on techniques related to dynamic shape acquisition and reconstruction. In particular, we review different approaches for representing the deformation field, and the methods for computing the desired deformation. Both optimization-based and learning-based methods are covered. We also review benchmarks and datasets for evaluating non-rigid registration methods, and discuss potential future research directions.

show abstract

Section: Extrinsic Methodsmentioning

confidence: 99%

Section: Extrinsic Methodsmentioning

confidence: 99%

Section: Extrinsic Methodsmentioning

confidence: 99%

Section: Extrinsic Methodsmentioning

confidence: 99%

See 2 more Smart Citations

A Survey of Non‐Rigid 3D Registration

Deng

Yao

Dyke

et al. 2022

Computer Graphics Forum

View full text Add to dashboard Cite

show abstract

“…Basically, it deforms the vertices of a model to fit the observations at each time step using a non-rigid deformation [22][23][24]. The asrigid-as-possible method [22] is commonly used to regularize deformable surfaces [25][26][27][28][29][30][31]. Zollhöfer et al [26] proposed a novel GPU (graphics processing unit) pipeline for non-rigid registration of live RGB-D (color and depth) data to a smooth template using an extended nonlinear as-rigid-as-possible framework.…”

Section: Non-rigid Registrationmentioning

confidence: 99%

High-Speed Dynamic Projection Mapping onto Human Arm with Realistic Skin Deformation

Peng

Watanabe

2021

Applied Sciences

View full text Add to dashboard Cite

Dynamic projection mapping for a moving object according to its position and shape is fundamental for augmented reality to resemble changes on a target surface. For instance, augmenting the human arm surface via dynamic projection mapping can enhance applications in fashion, user interfaces, prototyping, education, medical assistance, and other fields. For such applications, however, conventional methods neglect skin deformation and have a high latency between motion and projection, causing noticeable misalignment between the target arm surface and projected images. These problems degrade the user experience and limit the development of more applications. We propose a system for high-speed dynamic projection mapping onto a rapidly moving human arm with realistic skin deformation. With the developed system, the user does not perceive any misalignment between the arm surface and projected images. First, we combine a state-of-the-art parametric deformable surface model with efficient regression-based accuracy compensation to represent skin deformation. Through compensation, we modify the texture coordinates to achieve fast and accurate image generation for projection mapping based on joint tracking. Second, we develop a high-speed system that provides a latency between motion and projection below 10 ms, which is generally imperceptible by human vision. Compared with conventional methods, the proposed system provides more realistic experiences and increases the applicability of dynamic projection mapping.

show abstract