Inferring a globally consistent normal orientation for point clouds remains challenging, especially for noisy and non-watertight point clouds. To improve accuracy and robustness in orientation inference, a Boundary-Aware Consistent Normal Orientation (BACNO) method is proposed. Its main idea is to transform the normal orientation problem into a boundary-aware narrow band grid partitioning problem. This processing process is as follows: First, an unsigned distance field for an input point cloud is computed, which is defined on a regular grid. The field is then trimmed as a boundary-aware narrow band grid around the point cloud. Next, the narrow band grid is segmented into two parts, with each part located on one side of the input point cloud. Finally, a coarse-to-fine normal orientation strategy is presented to achieve the globally consistent orientation. Extensive experimental results demonstrate that the proposed method outperforms state-of-the-art methods, particularly for noisy and non-watertight point clouds.

Abstract Restoring the appearance of the model is a crucial step for achieving realistic 3D reconstruction. High‐fidelity textures can also conceal some geometric defects. Since the estimated camera parameters and reconstructed geometry usually contain errors, subsequent texture mapping often suffers from undesirable visual artifacts such as blurring, ghosting, and visual seams. In particular, significant misalignment between the reconstructed model and the registered images will lead to texturing the mesh with inconsistent image regions. However, eliminating various artifacts to generate high‐quality textures remains a challenge. In this paper, we address this issue by designing a texture optimization method to generate seamless and aligned textures for 3D reconstruction. The main idea is to detect misalignment regions between images and geometry and exclude them from texture mapping. To handle the texture holes caused by these excluded regions, a cross‐patch texture hole‐filling method is proposed, which can also synthesize plausible textures for invisible faces. Moreover, for better stitching of the textures from different views, an improved camera pose optimization is present by introducing color adjustment and boundary point sampling. Experimental results show that the proposed method can eliminate the artifacts caused by inaccurate input data robustly and produce high‐quality texture results compared with state‐of‐the‐art methods.

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 performed on the track-graph to partition the scene into 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.

Abstract This paper proposes a passive multi‐view system for human body shape reconstruction, namely RHF‐Human, to overcome several challenges including accurate calibration and stereo matching in self‐occluded and low‐texture skin regions. The reconstruction process includes four steps: capture, multi‐view camera calibration, dense reconstruction, and meshing. The capture system, which consists of 90 digital single‐lens reflex cameras, is single‐shot to avoid nonrigid deformation of the human body. Two technical contributions are made: (1) a two‐step robust multi‐view calibration approach that improves calibration accuracy and saves calibration time for each new human body acquired and (2) an accurate PatchMatch multi‐view stereo method for dense reconstruction to perform correct matching in self‐occluded and low‐texture skin regions and to reduce the noise caused by body hair. Experiments on models of various genders, poses, and skin with different amounts of body hair show the robustness of the proposed system. A high‐fidelity human body shape dataset with 227 models is constructed, and the average accuracy is within 1.5 mm. The system provides a new scheme for the accurate reconstruction of nonrigid human models based on passive vision and has good potential in fashion design and health care.