Zhen Ni

Zhen Ni, Guitao Cao, Ye Duan

Researches of analysis and parsing around façades to enrich the 3D feature of façade models by semantic information raised some attention in the community, whose main idea is to generate higher resolution components with similar shapes and textures to increase the overall resolution at the expense of reconstruction accuracy. While this approach works well for components like windows and doors, there is no solution for façade background at present. In this paper, we introduce the concept of representative region texture, which can be used in the above modeling approach by tiling the representative texture around the façade region, and propose a semi-supervised way to do representative region texture extraction from a façade image. Our method does not require any additional labelled data to train as long as the semantic information is given, while a traditional end-to-end model requires plenty of data to increase its performance. Our method can extract texture from any repetitive images, not just façade, which is not capable in an end-to-end model as it relies on the distribution of training set. Clustering with weighted distance is introduced to further increase the robustness to noise or an imprecise segmentation, and make the extracted texture have a higher resolution and more suitable for tiling. We verify our method on various façade images, and the result shows our method has a significant performance improvement compared to only a random crop on façade. We also demonstrate some application scenarios and proposed a façade modeling workflow with the representative region texture, which has a better visual resolution for a regular façade.

Yiran Pang, Zhen Ni, Xiangnan Zhong

Federated reinforcement learning (FedRL) enables multiple agents to collaboratively train a global policy without sharing raw data, making it ideal for privacy-sensitive applications. However, FedRL faces challenges in heterogeneous environments where differing state-transition dynamics lead to non-identical input distributions and imbalanced parameter updates during aggregation. Therefore, this paper develops a personalized observation normalization (PON) method, allowing each agent to locally normalize raw state inputs using a continuously updated running mean and variance. This design ensures consistent scaling of local feature without overshadowing across agents during aggregation. Furthermore, we demonstrate that sharing normalization parameters across agents is ineffective due to the diverse local input distributions, which highlights the necessity of personalized statistics. Experiments on heterogeneous MuJoCo tasks show that our developed PON accelerates training and achieves superior performance compared to baseline methods.