Space-time Neural Irradiance Fields for Free-Viewpoint Video
This work is significant for researchers and practitioners in computer graphics and vision, offering a new approach to free-viewpoint video synthesis from limited input, which is an incremental improvement over existing methods.
This paper introduces a method to learn a spatiotemporal neural irradiance field for dynamic scenes from a single video, enabling free-viewpoint rendering. It addresses the ambiguity of varying geometry and appearance by constraining the time-varying geometry using estimated scene depth.
We present a method that learns a spatiotemporal neural irradiance field for dynamic scenes from a single video. Our learned representation enables free-viewpoint rendering of the input video. Our method builds upon recent advances in implicit representations. Learning a spatiotemporal irradiance field from a single video poses significant challenges because the video contains only one observation of the scene at any point in time. The 3D geometry of a scene can be legitimately represented in numerous ways since varying geometry (motion) can be explained with varying appearance and vice versa. We address this ambiguity by constraining the time-varying geometry of our dynamic scene representation using the scene depth estimated from video depth estimation methods, aggregating contents from individual frames into a single global representation. We provide an extensive quantitative evaluation and demonstrate compelling free-viewpoint rendering results.