Fast High Dynamic Range Radiance Fields for Dynamic Scenes
This work addresses the limitation of HDR in dynamic scenes for applications like 3D reconstruction and view synthesis, though it appears incremental as it builds on existing HDR NeRF methods.
The paper tackles the problem of extending high-dynamic-range (HDR) techniques to dynamic scenes in Neural Radiance Fields (NeRF), which previously focused on static scenes, by proposing HDR-HexPlane to learn 3D scenes from dynamic images with various exposures, enabling rendering of high-quality novel-view images at any time and exposure.
Neural Radiances Fields (NeRF) and their extensions have shown great success in representing 3D scenes and synthesizing 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 static scenes. To extend HDR NeRF methods to wider applications, we propose a dynamic HDR NeRF framework, named 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 are available at \url{https://guanjunwu.github.io/HDR-HexPlane/}.