PlatoNeRF: 3D Reconstruction in Plato's Cave via Single-View Two-Bounce Lidar
This addresses the problem of accurate 3D reconstruction from a single view for applications in consumer devices like phones and tablets, representing a novel method rather than an incremental improvement.
The paper tackles the challenge of single-view 3D reconstruction by using time-of-flight lidar data to model two-bounce optical paths with NeRF, enabling reconstruction of visible and occluded geometry without data priors or controlled lighting, and demonstrates improved generalization under sensor constraints.
3D reconstruction from a single-view is challenging because of the ambiguity from monocular cues and lack of information about occluded regions. Neural radiance fields (NeRF), while popular for view synthesis and 3D reconstruction, are typically reliant on multi-view images. Existing methods for single-view 3D reconstruction with NeRF rely on either data priors to hallucinate views of occluded regions, which may not be physically accurate, or shadows observed by RGB cameras, which are difficult to detect in ambient light and low albedo backgrounds. We propose using time-of-flight data captured by a single-photon avalanche diode to overcome these limitations. Our method models two-bounce optical paths with NeRF, using lidar transient data for supervision. By leveraging the advantages of both NeRF and two-bounce light measured by lidar, we demonstrate that we can reconstruct visible and occluded geometry without data priors or reliance on controlled ambient lighting or scene albedo. In addition, we demonstrate improved generalization under practical constraints on sensor spatial- and temporal-resolution. We believe our method is a promising direction as single-photon lidars become ubiquitous on consumer devices, such as phones, tablets, and headsets.