Transparent object manipulation remains a significant challenge in robotics due to the difficulty of acquiring accurate and dense depth measurements. Conventional depth sensors often fail with transparent objects, resulting in incomplete or erroneous depth data. Existing depth completion methods struggle with interframe consistency and incorrectly model transparent objects as Lambertian surfaces, leading to poor depth reconstruction. To address these challenges, we propose TranSplat, a surface embedding-guided 3D Gaussian Splatting method tailored for transparent objects. TranSplat uses a latent diffusion model to generate surface embeddings that provide consistent and continuous representations, making it robust to changes in viewpoint and lighting. By integrating these surface embeddings with input RGB images, TranSplat effectively captures the complexities of transparent surfaces, enhancing the splatting of 3D Gaussians and improving depth completion. Evaluations on synthetic and real-world transparent object benchmarks, as well as robot grasping tasks, show that TranSplat achieves accurate and dense depth completion, demonstrating its effectiveness in practical applications. We open-source synthetic dataset and model: https://github.com/jeongyun0609/TranSplat

The insufficient number of annotated thermal infrared (TIR) image datasets not only hinders TIR image-based deep learning networks to have comparable performances to that of RGB but it also limits the supervised learning of TIR image-based tasks with challenging labels. As a remedy, we propose a modified multidomain RGB to TIR image translation model focused on edge preservation to employ annotated RGB images with challenging labels. Our proposed method not only preserves key details in the original image but also leverages the optimal TIR style code to portray accurate TIR characteristics in the translated image, when applied on both synthetic and real world RGB images. Using our translation model, we have enabled the supervised learning of deep TIR image-based optical flow estimation and object detection that ameliorated in deep TIR optical flow estimation by reduction in end point error by 56.5% on average and the best object detection mAP of 23.9% respectively. Our code and supplementary materials are available at https://github.com/rpmsnu/sRGB-TIR.

The awareness for preserving privacy in in-home monitoring robots is increasing. Although several studies have proposed privacy-preserved in-home monitoring robot systems for adults, only a limited amount of attention has been paid attention to research on privacy-preserved in-home monitoring of babies. Like previous studies, thermal infrared image-based methods could ensure a privacy-preserved monitoring of babies, yet when existing detection methods were applied to thermal images to detect babies and adults, we discovered a frequent occurrence of misdetection due to the presence of thermal residual heat marks. In this research, we propose a sequential thermal image-based detection that conjugated the characteristics of thermal residual heat marks. The proposed detection reduced misdetection caused by thermal residual heat marks by 98.7% when compared to RetinaNet. In addition, we open-source our collected thermal image-based baby and adult dataset via: https://github.com/donkeymouse/ThermalAdultandBaby.

Face spoofing detection could be used in conjunction with face recognition or facial expression recognition in social robots for better interaction with the users. Recent works have employed thermal image-based spoofing detection due to its competitive spoofing detection performance. However, existing methods utilized indoor thermal images which put a limit on using thermal image-based spoofing detection in outdoor environments. Moreover, several thermal image-based spoofing detection datasets consist of facial images at a frontal viewpoint, which would be put a limit on the usage in social robots with short heights. In this paper, we present our novel thermal image dataset for spoofing detection in outdoor environments. Unlike most existing datasets, our dataset is collected in outdoor environments with the camera facing the upper view to simulate the viewpoint of a social robot. To cover diverse outdoor environments, the dataset was collected at varying locations, times, and weather. Furthermore, we trained an event recognition-based spoofing detection on our collected dataset and also have provided benchmarking results for several baselines. Our spoofing detection method based on MobileNetV2 yielded a spoofing detection accuracy of 96.04% and GFLOPs of 0.88. Our dataset will be open-sourced for users pursuing academic research and will be available upon request to the authors.