Fabricating and designing 3D garments has become extremely demanding with the increasing need for synthesizing realistic dressed persons for a variety of applications, e.g. 3D virtual try-on, digitalization of 2D clothes into 3D apparel, and cloth animation. It thus necessitates a simple and straightforward pipeline to obtain high-quality texture from simple input, such as 2D reference images. Since traditional warping-based texture generation methods require a significant number of control points to be manually selected for each type of garment, which can be a time-consuming and tedious process. We propose a novel method, called Cloth2Tex, which eliminates the human burden in this process. Cloth2Tex is a self-supervised method that generates texture maps with reasonable layout and structural consistency. Another key feature of Cloth2Tex is that it can be used to support high-fidelity texture inpainting. This is done by combining Cloth2Tex with a prevailing latent diffusion model. We evaluate our approach both qualitatively and quantitatively and demonstrate that Cloth2Tex can generate high-quality texture maps and achieve the best visual effects in comparison to other methods. For more details and animated results, please see https://tomguluson92. github.io/projects/cloth2tex/.

The current interacting hand (IH) datasets are relatively simplistic in terms of background and texture, with hand joints being annotated by a machine annotator, which may result in inaccuracies, and the diversity of pose distribution is limited. However, the variability of background, pose distribution, and texture can greatly influence the generalization ability. Therefore, we present a large-scale synthetic dataset –RenderIH– for interacting hands with accurate and diverse pose annotations. The dataset contains 1M photo-realistic images with varied backgrounds, perspectives, and hand textures. To generate natural and diverse interacting poses, we propose a new pose optimization algorithm. Additionally, for better pose estimation accuracy, we introduce a transformer-based pose estimation network, TransHand, to leverage the correlation between interacting hands and verify the effectiveness of RenderIH in improving results. Our dataset is model-agnostic and can improve more accuracy of any hand pose estimation method in comparison to other real or synthetic datasets. Experiments have shown that pretraining on our synthetic data can significantly decrease the error from 6.76mm to 5.79mm, and our Transhand surpasses contemporary methods. Our dataset and code are available at https://github.com/adwardlee/RenderIH.

Current methods for 3D hand pose estimation fail to generalize well to in-the-wild new scenarios due to varying camera viewpoints, self-occlusions, and complex environments. To address this problem, we propose CycleHand to improve the generalization ability of the model in a self-supervised manner. Our motivation is based on an observation: if one globally rotates the whole hand and reversely rotates it back, the estimated 3D poses of fingers should keep consistent before and after the rotation because the wrist-relative hand poses stay unchanged during global 3D rotation. Hence, we propose arbitrary-rotation self-supervised consistency learning to improve the model's robustness for varying viewpoints. Another innovation of CycleHand is that we propose a high-fidelity texture map to render the photorealistic rotated hand with different lighting conditions, backgrounds, and skin tones to further enhance the effectiveness of our self-supervised task. To reduce the potential negative effects brought by the domain shift of synthetic images, we use the idea of contrastive learning to learn a synthetic-real consistent feature extractor in extracting domain-irrelevant hand representations. Experiments show that CycleHand can largely improve the hand pose estimation performance in both canonical datasets and real-world applications.

Abstract The development of unmanned aerial vehicles has been identified as a potential source of a weapon for causing operational disruptions against critical infrastructures. To mitigate and neutralise the threat posed by the misuse of drones against malicious and terrorist activity, this paper presents a holistic design of a long-range autonomous drone detection platform. The novelty of the proposed system lies in the confluence between the design of hardware and software components to effective and efficient localisation of the intruder objects. The research presented in the paper proposes the design and validation of a situation awareness component which is interfaced with the hardware component for controlling the focal length of the camera. The continuous stream of media data obtained from the region of vulnerability is processed using the object detection that is built on region based fully connected neural network. The novelty of the proposed system relies on the processing of multi-threaded dual-media input streams that are evaluated to mitigate the latency of the system. Upon the successful detection of malicious drones, the system logs the occurrence of intruders that consists of both event description and the associated media evidence for the deployment of the mitigation strategy. The analytics platform that controls the signalling of the low-cost sensing equipment contains the NVIDIA GeForce GTX 1080 for detecting drones. The experimental testbeds developed for the validation of the proposed system has been constructed to include environments and situations that are commonly faced by critical infrastructure operators such as the area of protection, drone flight path, tradeoff between the angle of coverage against the distance of coverage. The validation of the proposed system has resulted in yielding a range of intruder drone detection by 250m with an accuracy of 95.5%.