Related papers: Realistic Bokeh Effect Rendering on Mobile GPUs, M…

Real-time low-light image enhancement on mobile and embedded devices requires models that balance visual quality and computational efficiency. Existing deep learning methods often rely on large networks and labeled datasets, limiting their…

This paper presents the concept of AI-supported Mini-Labs, combining smartphone-based experiments with multimodal large language models (MLLMs). Smartphones, with their integrated sensors and computational power, function as versatile…

Over the last years, the computational power of mobile devices such as smartphones and tablets has grown dramatically, reaching the level of desktop computers available not long ago. While standard smartphone apps are no longer a problem…

Deep Learning (DL) has shown impressive performance in many mobile applications. Most existing works have focused on reducing the computational and resource overheads of running Deep Neural Networks (DNN) inference on resource-constrained…

Low-light image enhancement (LLIE) aims at improving the perception or interpretability of an image captured in an environment with poor illumination. Recent advances in this area are dominated by deep learning-based solutions, where many…

We present Blendshapes GHUM, an on-device ML pipeline that predicts 52 facial blendshape coefficients at 30+ FPS on modern mobile phones, from a single monocular RGB image and enables facial motion capture applications like virtual avatars.…

We introduce BokehDiff, a novel lens blur rendering method that achieves physically accurate and visually appealing outcomes, with the help of generative diffusion prior. Previous methods are bounded by the accuracy of depth estimation,…

This article proposes and documents a machine-learning framework and tutorial for classifying images using mobile phones. Compared to computers, the performance of deep learning model performance degrades when deployed on a mobile phone and…

This work tackles the challenging task of achieving real-time novel view synthesis for reflective surfaces across various scenes. Existing real-time rendering methods, especially those based on meshes, often have subpar performance in…

Recently, significant progress has been achieved in deep image matting. Most of the classical image matting methods are time-consuming and require an ideal trimap which is difficult to attain in practice. A high efficient image matting…

A shallow depth-of-field image keeps the subject in focus, and the foreground and background contexts blurred. This effect requires much larger lens apertures than those of smartphone cameras. Conventional methods acquire RGB-D images and…

We present BlazeFace, a lightweight and well-performing face detector tailored for mobile GPU inference. It runs at a speed of 200-1000+ FPS on flagship devices. This super-realtime performance enables it to be applied to any augmented…

Autonomous mobile systems increasingly rely on deep neural networks for perception and decision-making. While effective, these systems are vulnerable to adversarial machine learning attacks where minor input perturbations can significantly…

The increased importance of mobile photography created a need for fast and performant RAW image processing pipelines capable of producing good visual results in spite of the mobile camera sensor limitations. While deep learning-based…

Deep learning solutions are being increasingly used in mobile applications. Although there are many open-source software tools for the development of deep learning solutions, there are no guidelines in one place in a unified manner for…

Existing neural head avatars methods have achieved significant progress in the image quality and motion range of portrait animation. However, these methods neglect the computational overhead, and to the best of our knowledge, none is…

Recent breakthroughs in deep learning and artificial intelligence technologies have enabled numerous mobile applications. While traditional computation paradigms rely on mobile sensing and cloud computing, deep learning implemented on…

We present an exploration of machine learning architectures for predicting brain responses to realistic images on occasion of the Algonauts Challenge 2023. Our research involved extensive experimentation with various pretrained models.…

We present an end-to-end neural network-based model for inferring an approximate 3D mesh representation of a human face from single camera input for AR applications. The relatively dense mesh model of 468 vertices is well-suited for…

We propose BokehMe, a hybrid bokeh rendering framework that marries a neural renderer with a classical physically motivated renderer. Given a single image and a potentially imperfect disparity map, BokehMe generates high-resolution…