Albeit remarkable progress has been made to improve the accuracy and completeness of multi-view stereo (MVS), existing methods still suffer from either sparse reconstructions of low-textured surfaces or heavy computational burden. In this paper, we propose a Confidence-based Large-scale Dense Multi-view Stereo (CLD-MVS) method for high resolution imagery. Firstly, we formulate MVS as a multi-view depth estimation problem, and employ a normal-aware efficient PatchMatch stereo to estimate the initial depth and normal map for each reference view. A self-supervised deep learning method is then developed to predict the spatial confidence for multi-view depth maps, which is combined with cross-view consistency to generate the ground control points. Subsequently, a confidence-driven and boundary-aware interpolation scheme using static and dynamic guidance is adopted to synthesize dense depth and normal maps. Finally, a refinement procedure which leverages synthesized depth and normal as prior is conducted to estimate cross-view consistent surface. Experiments show that the proposed CLD-MVS method achieves high geometric completeness while preserving fine-scale details. In particular, it has ranked No. 1 on the ETH3D high-resolution MVS benchmark in terms of $F_{1}$ -score.

Unmanned aerial vehicles (UAVs) can capture high-quality aerial photos and have been widely used for large-scale urban 3D reconstruction. However, even with the help of commercial flight control software, it is still a challenging task for non-professional users to capture full-coverage aerial photos in complex urban environments, which normally leads to incomplete 3D reconstruction. In this paper, we propose a novel path planning method for the high-quality aerial 3D reconstruction of urban scenes. The proposed approach first captures aerial photos, following an initial path to generate a coarse 3D model as prior knowledge. Then, 3D viewpoints with constrained location and orientation are generated and evaluated, according to the completeness and accuracy of the corresponding visible regions of the prior model. Finally, an optimized path is produced by smoothly connecting the optimal viewpoints. We perform an extensive evaluation of our method on real and simulated data sets, in comparison with a state-of-the-art method. The experimental results indicate that the optimized trajectory generated by our method can lead to a significant boost in the performance of aerial 3D urban reconstruction.

Continuous sign language recognition (CSLR) is an essential task for communication between hearing-impaired and people without limitations, which aims at aligning low-density video sequences with high-density text sequences. The current methods for CSLR were mainly based on convolutional neural networks. However, these methods perform poorly in balancing spatial and temporal features during visual feature extraction, making them difficult to improve the accuracy of recognition. To address this issue, we designed an end-to-end CSLR network: Spatial–Temporal Transformer Network (STTN). The model encodes and decodes the sign language video as a predicted sequence that is aligned with a given text sequence. First, since the image sequences are too long for the model to handle directly, we chunk the sign language video frames, i.e., ”image to patch”, which reduces the computational complexity. Second, global features of the sign language video are modeled at the beginning of the model, and the spatial action features of the current video frame and the semantic features of consecutive frames in the temporal dimension are extracted separately, giving rise to fully extracting visual features. Finally, the model uses a simple cross-entropy loss to align video and text. We extensively evaluated the proposed network on two publicly available datasets, CSL and RWTH-PHOENIX-Weather multi-signer 2014 (PHOENIX-2014), which demonstrated the superior performance of our work in CSLR task compared to the state-of-the-art methods.

In this paper, we introduce Segmentation-Driven Deformation Multi-View Stereo (SD-MVS), a method that can effectively tackle challenges in 3D reconstruction of textureless areas. We are the first to adopt the Segment Anything Model (SAM) to distinguish semantic instances in scenes and further leverage these constraints for pixelwise patch deformation on both matching cost and propagation. Concurrently, we propose a unique refinement strategy that combines spherical coordinates and gradient descent on normals and pixelwise search interval on depths, significantly improving the completeness of reconstructed 3D model. Furthermore, we adopt the Expectation-Maximization (EM) algorithm to alternately optimize the aggregate matching cost and hyperparameters, effectively mitigating the problem of parameters being excessively dependent on empirical tuning. Evaluations on the ETH3D high-resolution multi-view stereo benchmark and the Tanks and Temples dataset demonstrate that our method can achieve state-of-the-art results with less time consumption.

Patch deformation-based methods have recently exhibited substantial effectiveness in multi-view stereo, due to the incorporation of deformable and expandable perception to reconstruct textureless areas. However, such approaches typically focus on exploring correlative reliable pixels to alleviate match ambiguity during patch deformation, but ignore the deformation instability caused by mistaken edge-skipping and visibility occlusion, leading to potential estimation deviation. To remedy the above issues, we propose DVP-MVS, which innovatively synergizes depth-edge aligned and cross-view prior for robust and visibility-aware patch deformation. Specifically, to avoid unexpected edge-skipping, we first utilize Depth Anything V2 followed by the Roberts operator to initialize coarse depth and edge maps respectively, both of which are further aligned through an erosion-dilation strategy to generate fine-grained homogeneous boundaries for guiding patch deformation. In addition, we reform view selection weights as visibility maps and restore visible areas by cross-view depth reprojection, then regard them as cross-view prior to facilitate visibility-aware patch deformation. Finally, we improve propagation and refinement with multi-view geometry consistency by introducing aggregated visible hemispherical normals based on view selection and local projection depth differences based on epipolar lines, respectively. Extensive evaluations on ETH3D and Tanks & Temples benchmarks demonstrate that our method can achieve state-of-the-art performance with excellent robustness and generalization.