Monocular depth estimation is a traditional computer vision task that predicts the distance of each pixel relative to the camera from one 2D image. Relative height information about objects lying on a ground plane can be calculated through several processing steps from the depth image. In this paper, we propose a height estimation method for directly predicting the height of objects from a 2D image. The proposed method utilizes an encoder-decoder network for pixel-wise dense prediction based on height consistency. We used the CARLA simulator to generate 40,000 training datasets from different positions in five areas within the simulator. The experimental results show that the object’s height map can be estimated regardless of the camera’s location.

Privacy protection in the computer vision field has attracted increasing attention. Generative adversarial network-based methods have been explored for identity anonymization, but they do not take into consideration semantic information of images, which may result in unrealistic or flawed facial results. In this paper, we propose a Semantic-aware De-identification Generative Adversarial Network (SDGAN) model for identity anonymization. To retain the facial expression effectively, we extract the facial semantic image using the edge-aware graph representation network to constraint the position, shape and relationship of generated facial key features. Then the semantic image is injected into the generator together with the randomly selected identity information for de-Identification. To ensure the generation quality and realistic-looking results, we adopt the SPADE architecture to improve the generation ability of conditional GAN. Meanwhile, we design a hybrid identity discriminator composed of an image quality analysis module, a VGG-based perceptual loss function, and a contrastive identity loss to enhance both the generation quality and ID anonymization. A comparison with the state-of-the-art baselines demonstrates that our model achieves significantly improved de-identification (De-ID) performance and provides more reliable and realistic-looking generated faces. Our code and data are available on https://github.com/kimhyeongbok/SDGAN

This paper proposes a deep learning framework for decreasing large-scale domain shift problems in object detection using domain adaptation techniques. We have approached data-centric domain adaptation with Image-to-Image translation models for this problem. It is one of the methodologies that changes source data to target domain's style by reducing domain shift. However, the method cannot be applied directly to the domain adaptation task because the existing Image-to-Image model focuses on style translation. We solved this problem using the data-centric approach simply by reordering the training sequence of the domain adaptation model. We defined the features to be content and style. We hypothesized that object-specific information in images was more closely tied to the content than the style and thus experimented with methods to preserve content information before style was learned. We trained the model separately only by altering the training data. Our experiments confirmed that the proposed method improves the performance of the domain adaptation model and increases the effectiveness of using the generated synthetic data for training object detection models. We compared our approach with the existing single-stage method where content and style were trained simultaneously. We argue that our proposed method is more practical for training object detection models than others. The emphasis in this study is to preserve image content while changing the style of the image. In the future, we plan to conduct additional experiments to apply synthetic data generation technology to various other application areas like indoor scenes and bin picking.