Search for: All records

We present a method to reconstruct dynamic scenes from monocular continuous-wave time-of-flight (C-ToF) cameras using raw sensor samples that achieves similar or better accuracy than neural volumetric approaches and is 100×faster. Quickly achieving high-fidelity dynamic 3D reconstruction from a single viewpoint is a significant challenge in computer vision. In C-ToF radiance field reconstruction, the property of interest—depth—is not directly measured, causing an additional challenge. This problem has a large and underappreciated impact upon the optimization when using a fast primitive-based scene representation like 3D Gaussian splatting, which is commonly used with multi-view data to produce satisfactory results and is brittle in its optimization otherwise. We incorporate two heuristics into the optimization to improve the accuracy of scene geometry represented by Gaussians. Experimental results show that our approach produces accurate reconstructions under constrained C-ToF sensing conditions, including for fast motions like swinging baseball bats. https://visual.cs.brown.edu/gftorf 

We exploit memory effect correlations in speckles for the imaging of incoherent fluorescent sources behind scattering tissue. These correlations are often weak when imaging thick scattering tissues and complex illumination patterns, both of which greatly limit the practicality of associated techniques. In this work, we introduce a spatial light modulator between the tissue sample and the imaging sensor and capture multiple modulations of the speckle pattern. We show that by correctly designing the modulation patterns and the associated reconstruction algorithm, statistical correlations in the measurements can be greatly enhanced. We exploit this to demonstrate the reconstruction of mega-pixel sized fluorescent patterns behind the scattering tissue.