A Robust Multi‐View System for High‐Fidelity Human Body Shape Reconstruction

Zhang, Qitong; Wang, Lei; Liu, Ge; Luo, Shan; Zhu, Taihao; Jiang, Feng; Ding, Jimmy; Feng, Jieqing

doi:10.1111/cgf.14354

Cited by 5 publications

(2 citation statements)

References 88 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We also apply our method to eight datasets with ground truth to quantitatively evaluate the accuracy compared with four state-of-the-art SfM approaches, namely, COLMAP [9], GraphSfM [15], the global system of Theia [41] and PixSfM [40]. Our human body acquisition system is equipped with 90 cameras and deployed in a cylindrical shape [44]. The human body is located at the center of the cylinder.…”

Section: Application In Human Body Reconstructionmentioning

confidence: 99%

TC-SfM: Robust Track-Community-Based Structure-from-Motion

Wang¹,

Liu²,

Si³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Structure-from-Motion (SfM) aims to recover 3D scene structures and camera poses based on the correspondences between input images, and thus the ambiguity caused by duplicate structures (i.e., different structures with strong visual resemblance) always results in incorrect camera poses and 3D structures. To deal with the ambiguity, most existing studies resort to additional constraint information or implicit inference by analyzing two-view geometries or feature points. In this paper, we propose to exploit high-level information in the scene, i.e., the spatial contextual information of local regions, to guide the reconstruction. Specifically, a novel structure is proposed, namely, track-community, in which each community consists of a group of tracks and represents a local segment in the scene. A community detection algorithm is used to partition the scene into several segments. Then, the potential ambiguous segments are detected by analyzing the neighborhood of tracks and corrected by checking the pose consistency. Finally, we perform partial reconstruction on each segment and align them with a novel bidirectional consistency cost function which considers both 3D-3D correspondences and pairwise relative camera poses. Experimental results demonstrate that our approach can robustly alleviate reconstruction failure resulting from visually indistinguishable structures and accurately merge the partial reconstructions.

show abstract

Section: Application In Human Body Reconstructionmentioning

confidence: 99%

TC-SfM: Robust Track-Community-Based Structure-from-Motion

Wang¹,

Liu²,

Si³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…The high‐fidelity 3D model of clothed human is crucial in many graphic related applications, including virtual reality, digital human, and virtual try‐on, and so on, which requires the reconstruction of clothed human with arbitrary postures and clothing details (style, wrinkles and clothed layers) from details and accurate feature representation. Considering the monocular images are more available than camera matrix [ZWG*21], many images‐based methods using high‐capacity deep learning models have been proposed for the clothed human reconstruction recently. For instance, Zhu et al.…”

Section: Introductionmentioning

confidence: 99%

Feature Representation for High‐resolution Clothed Human Reconstruction

Liu

et al. 2023

Computer Graphics Forum

View full text Add to dashboard Cite

Detailed and accurate feature representation is essential for high‐resolution reconstruction of clothed human. Herein we introduce a unified feature representation for clothed human reconstruction, which can adapt to changeable posture and various clothing details. The whole method can be divided into two parts: the human shape feature representation and the details feature representation. Specifically, we firstly combine the voxel feature learned from semantic voxel with the pixel feature from input image as an implicit representation for human shape. Then, the details feature mixed with the clothed layer feature and the normal feature is used to guide the multi‐layer perceptron to capture geometric surface details. The key difference from existing methods is that we use the clothing semantics to infer clothed layer information, and further restore the layer details with geometric height. We qualitative and quantitative experience results demonstrate that proposed method outperforms existing methods in terms of handling limb swing and clothing details. Our method provides a new solution for clothed human reconstruction with high‐resolution details (style, wrinkles and clothed layers), and has good potential in three‐dimensional virtual try‐on and digital characters.

show abstract

Type-based outlier removal framework for point clouds

Liu

Feng

2021

Information Sciences

View full text Add to dashboard Cite

A Robust Multi‐View System for High‐Fidelity Human Body Shape Reconstruction

Cited by 5 publications

References 88 publications

TC-SfM: Robust Track-Community-Based Structure-from-Motion

TC-SfM: Robust Track-Community-Based Structure-from-Motion

Feature Representation for High‐resolution Clothed Human Reconstruction

Type-based outlier removal framework for point clouds

Contact Info

Product

Resources

About