Neural Field Representations of Mobile Computational Photography
By: Ilya Chugunov
Potential Business Impact:
Makes phones create amazing 3D pictures from photos.
Over the past two decades, mobile imaging has experienced a profound transformation, with cell phones rapidly eclipsing all other forms of digital photography in popularity. Today's cell phones are equipped with a diverse range of imaging technologies - laser depth ranging, multi-focal camera arrays, and split-pixel sensors - alongside non-visual sensors such as gyroscopes, accelerometers, and magnetometers. This, combined with on-board integrated chips for image and signal processing, makes the cell phone a versatile pocket-sized computational imaging platform. Parallel to this, we have seen in recent years how neural fields - small neural networks trained to map continuous spatial input coordinates to output signals - enable the reconstruction of complex scenes without explicit data representations such as pixel arrays or point clouds. In this thesis, I demonstrate how carefully designed neural field models can compactly represent complex geometry and lighting effects. Enabling applications such as depth estimation, layer separation, and image stitching directly from collected in-the-wild mobile photography data. These methods outperform state-of-the-art approaches without relying on complex pre-processing steps, labeled ground truth data, or machine learning priors. Instead, they leverage well-constructed, self-regularized models that tackle challenging inverse problems through stochastic gradient descent, fitting directly to raw measurements from a smartphone.
Similar Papers
A Neural Field-Based Approach for View Computation & Data Exploration in 3D Urban Environments
CV and Pattern Recognition
Finds best city views for planning and analysis.
nnMobileNet++: Towards Efficient Hybrid Networks for Retinal Image Analysis
CV and Pattern Recognition
Helps doctors find eye diseases faster and better.
Learning Neural Exposure Fields for View Synthesis
CV and Pattern Recognition
Makes 3D pictures look good in any light.