Egocentric vision has a wide range of applications for human-centric activity recognition. However, the use of the egocentric fisheye camera allows wide angle coverage but image distortion is introduced along with strong human body self-occlusion, which can impose significant challenges in data processing and model reconstruction. Unlike previous work only leveraging synthetic data for model training, this paper first presents a new real-world EgoCentric Human Action (ECHA) dataset. By using the self-supervised learning under multi-view constraints, we propose a simple yet effective framework, namely EgoFish3D, for egocentric 3D pose estimation from a single image in different real-world scenarios.

Photoacoustic microscopy (PAM) has gained increasing popularity in biomedical imaging, providing new opportunities for tissue monitoring and characterization. Resolution enhancement and denoising are two critical tasks for PAM image reconstruction and post-processing. With the development of deep learning techniques, Convolutional Neural Networks (CNN) have been used for PAM. However, there exist several inherent challenges for this approach. The available PAM datasets used for training are limited and pre-trained models with conventional pixel level constraints are error prone. This work presents a Unified PhotoAcoustic Microscopy image reconstruction Network (UPAMNet) for both image super-resolution and denoising. The proposed method takes advantage of deep image priors by incorporating three effective attention based modules and a mixed training constraint at both pixel and perception levels. With the proposed framework, transfer learning is used to mitigate the domain gaps between different datasets. The generalization ability of the model is evaluated in details and experimental results on different PAM datasets demonstrate the superior performance of the method compared to the current state-of-the-art.