29 May 2025 in Journal on Computing and Cultural Heritage
Mural image inpainting is far less explored compared to its natural image counterpart and remains largely unsolved. Most existing image-inpainting methods tend to take the target image as the only input and directly repair the damage to generate a visually plausible result. These methods obtain high performance in restoration or completion of some pre-defined objects, e.g., human face, fabric texture, and printed texts, etc., however, are not suitable for repairing murals with varying subjects and large damaged areas. Moreover, due to discrete colors in paints, mural inpainting may suffer from apparent color bias. To this end, in this paper, we propose a line drawing guided progressive mural inpainting method. It divides the inpainting process into two steps: structure reconstruction and color correction, implemented by a structure reconstruction network (SRN) and a color correction network (CCN), respectively. In structure reconstruction, SRN utilizes the line drawing as an assistant to achieve large-scale content authenticity and structural stability. In color correction, CCN operates a local color adjustment for missing pixels which reduces the negative effects of color bias and edge jumping. The proposed approach is evaluated against the current state-of-the-art image inpainting methods. Qualitative and quantitative results demonstrate the superiority of the proposed method in mural image inpainting. The codes and data are available at https://github.com/qinnzou/mural-image-inpainting.
24 October 2016 in The Visual Computer
14 February 2024 in IEEE Transactions on Intelligent Vehicles
Road extraction is a powerful technique support to autonomous driving as it provides routable road information for motion planning algorithms. High-resolution aerial images offer comprehensive road information, facilitating the establishment of efficient and accurate road networks to monitor road changes in a timely manner. However, widespread occlusions and abundant local details pose challenges to highly accurate and continuous extraction, especially in areas with road bifurcations. To simultaneously improve both accuracy and connectivity of road extraction, in this paper, we propose a novel approach TPEGAN to integrate pixel-level segmentation and graph inference based on road pixel enhancement. By generating road pixels enhanced images, the generative adversarial network exploits the consistency among road pixels to embed pixel-level accuracy into the segmentation module. The multi-scale dual-branch segmentation module employs graph convolution reasoning to capture dependencies across different spatial regions, maintaining the connectivity of road networks. Extensive experiments on three public datasets demonstrate that TPEGAN outperforms SOTA methods with a considerable performance gap. As the complexity of road networks increases, the performance of TPEGAN degrades more slowly than SOTA method. Even in challenging urban scenes where the proportion of road pixels is more than 15%, TPEGAN retains its high performance and achieves a rIoU of 0.664 with an APLS of 72.81%, amounting to improvements of 4.1% and 2.62% over SOTA method, respectively.
1 November 2018 in Chinese Journal of Electronics
This paper presents a way to face alignment by Coarse-to-fine shape estimation (CFSE). Head poses, facial expressions and other facial appearance attributes are estimated coarsely as well as the main landmarks will be detected. The entire shape will be further estimated. This paper constructs an independent Head pose classification (HPC) model based on convolutional neural network to estimate and classify head poses. With the classification result, the estimated facial appearance attributes and the detected landmarks, a more accurate shape will be constructed. That shape will be used as the initialized shape and optimized by cascaded regression to approximate the ground-truth shape. Experiments on two challenging database demonstrate that CFSE outperforms the state-of-the-art methods.
1 October 2019 in Computer Graphics Forum
16 January 2021 in Computer Graphics Forum