Reconstructing Continuous Light Field From Single Coded Image
This addresses the challenge of high-quality 3D scene reconstruction from limited input for applications in computational photography and computer vision, representing a novel integration rather than an incremental improvement.
The paper tackles the problem of reconstructing a continuous light field from a single coded image by integrating joint aperture-exposure coding with a neural radiance field (NeRF), enabling accurate and efficient reconstruction without test-time optimization.
We propose a method for reconstructing a continuous light field of a target scene from a single observed image. Our method takes the best of two worlds: joint aperture-exposure coding for compressive light-field acquisition, and a neural radiance field (NeRF) for view synthesis. Joint aperture-exposure coding implemented in a camera enables effective embedding of 3-D scene information into an observed image, but in previous works, it was used only for reconstructing discretized light-field views. NeRF-based neural rendering enables high quality view synthesis of a 3-D scene from continuous viewpoints, but when only a single image is given as the input, it struggles to achieve satisfactory quality. Our method integrates these two techniques into an efficient and end-to-end trainable pipeline. Trained on a wide variety of scenes, our method can reconstruct continuous light fields accurately and efficiently without any test time optimization. To our knowledge, this is the first work to bridge two worlds: camera design for efficiently acquiring 3-D information and neural rendering.