Fast High Dynamic Range Radiance Fields for Dynamic Scenes

Neural Radiances Fields (NeRF) and its extensions have shown great success to represent 3D scenes and synthesis novel-view images. However, most NeRF methods take in low-dynamic-range (LDR) images, which may lose details especially with nonuniform illumination. Some previous NeRF methods attempt to introduce high-dynamic-range (HDR) techniques but mainly target at static scenes. To extend HDR NeRF methods to wider applications, we propose a dynamic HDR NeRF framework, named as HDR-HexPlane, which can learn 3D scenes from dynamic 2D images captured with various exposures. A learnable exposure mapping function is constructed to obtain adaptive exposure values for each image. Based on the monotonically-increasing prior, a camera response function is designed for stable learning. With the proposed model, high-quality novel-view images at any time point can be rendered with any desired exposure. We further construct a dataset containing multiple dynamic scenes captured with diverse exposures for evaluation. All the datasets and code will be released.