Time of the Flight of the Gaussians: Optimizing Depth Indirectly in Dynamic Radiance Fields
This addresses the challenge of high-fidelity dynamic scene reconstruction from a single viewpoint for computer vision applications, but it is incremental as it builds on existing Gaussian splatting methods with heuristics.
They tackled dynamic 3D reconstruction from monocular continuous-wave time-of-flight cameras by optimizing depth indirectly in radiance fields, achieving similar or better accuracy than neural volumetric methods and being 100x faster.
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 100x 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