InnoPeak Technology
InnoPeak Technology Employees
No people found yet for this company.
InnoPeak Technology Company Information
InnoPeak Technology, headquartered in Palo Alto, California, specializes in cutting-edge research in smartphone technologies, including computer vision, video, and image processing. The company delivers algorithms and products designed to enhance end users’ daily interactions with technology, particularly smart devices, communication networks, and cloud services. InnoPeak Technology offers competitive compensation and equal employment opportunities to its workforce.
The company’s research portfolio includes real-time lighting estimation for augmented reality (AR), multi-person 3D pose estimation, and continuous-touch text entry for AR glasses. Notable innovations include a method for real-time lighting estimation from a single image using deep neural networks and differentiable screen-space rendering, and PoP-Net, which predicts multi-person 3D poses from a depth image, achieving state-of-the-art results.
InnoPeak Technology has also designed Continuous-touch T9 and Continuous-touch Dual Ring text entry interfaces for AR glasses and developed a pipeline for reconstructing 3D human avatars from a single image using GAN-based texture inference. The company proposed a novel approach combining geometric information from Visual-Inertial Odometry (VIO) with semantic information from object detectors for mobile AR and introduced a 3D-aware generative network for talking-head generation with rhythmic head motion.
Further contributions include an RGBD-based globally-consistent dense 3D reconstruction approach with online texturing, GIA-Net for low-light imaging which integrates global information to improve performance, and GCF-Net to enhance video action classifiers with minimal computation overhead. Additionally, InnoPeak Technology developed RCA-GAN for image super-resolution and noise reduction, achieving superior visual quality and performance, and methods for occlusion handling and collision detection in smartphone AR using Time-of-Flight (ToF) cameras.