Amodal instance segmentation, which aims to detect and segment both visible and invisible parts of objects in images, plays a crucial role in various applications, including autonomous driving, robotic manipulation, and scene understanding. While existing methods require training both front-end detectors and mask decoders jointly, this approach lacks flexibility and fails to leverage the strengths of pre-existing modal detectors. To address this limitation, we propose SAMEO, a novel framework that adapts the Segment Anything Model (SAM) as a versatile mask decoder capable of interfacing with various front-end detectors to enable mask prediction even for partially occluded objects. Acknowledging the constraints of limited amodal segmentation datasets, we introduce Amodal-LVIS, a large-scale synthetic dataset comprising 300K images derived from the modal LVIS and LVVIS datasets. This dataset significantly expands the training data available for amodal segmentation research. Our experimental results demonstrate that our approach, when trained on the newly extended dataset, including Amodal-LVIS, achieves remarkable zero-shot performance on both COCOA-cls and D2SA benchmarks, highlighting its potential for generalization to unseen scenarios.

State-of-the-art single-view 360° room layout reconstruction methods formulate the problem as a high-level 1D (per-column) regression task. On the other hand, traditional low-level 2D layout segmentation is simpler to learn and can represent occluded regions, but it requires complex post-processing for the targeting layout polygon and sacrifices accuracy. We present Seg2Reg to render 1D layout depth regression from the 2D segmentation map in a differentiable and occlusion-aware way, marrying the merits of both sides. Specifically, our model predicts floor-plan density for the input equirectangular 360° image. Formulating the 2D layout representation as a density field enables us to employ ‘flattened’ volume rendering to form 1D layout depth regression. In addition, we propose a novel 3D warping augmentation on layout to improve generalization. Finally, we re-implement recent room layout reconstruction methods into our codebase for benchmarking and explore modern backbones and training techniques to serve as the strong baseline. The code is at https://PanoLayoutStudio.github.io.

Internet of Things (IoT) has been widely utilized with artificial intelligence (AI). However, it requires substantial effort to integrate AI and big data with IoT. To mitigate this problem, AItalk was proposed. By treating AI as a cyber IoT device, we do not need to write code of the AI mechanism in the network applications, as traditional AI-based IoT applications did. This article describes how the AI tools such as scikit-learn and TensorLayer are accommodated as cyber IoT devices in AItalk, and extends AItalk for non-IoT applications. We use house valuation as an example to show how AItalk can flexibly include the factors that have significant impact on the house price. We show that by adding extra features other than housing profile features, the accuracy for the prediction (valuation) can be improved by 38%. We also investigated the communication overhead of the distributed AItalk structure, which is 3.7% for the computation of one house price valuation.

In this paper, we develop a model for emergency repair problems under large-scale supply-demand perturbations. The model formulation proposed in this paper has the following key features. First, a novel time-space network flow technique is adopted to generate detailed schedules for repair teams and allow dynamic updates of the network due to perturbations. Second, the original schedules prior to the perturbations are considered by controlling the total difference between the original schedule and the adjusted schedule. Third, to reduce computational complexity, the model is formulated with different levels of detail (individual teams versus a team group). The model is also formulated as a special mixed-integer network flow problem with side constraints, which is characterized as NP-hard. An ant-colony-system-based hybrid global search algorithm is developed to efficiently solve large-scale problems. To test how well the model formulation and the heuristic algorithm may perform in actual operations, we conduct a case study using actual data from the 1999 Chi-Chi earthquake in Taiwan. The results show that the proposed model and solution algorithm perform very well and thus have great potential for assisting with the making of emergency repair decisions in the event of disasters given large-scale perturbations in supply and demand.