HDR-NeRF: High Dynamic Range Neural Radiance Fields
This work addresses the challenge of HDR view synthesis for computer vision and graphics applications, representing an incremental improvement by extending NeRF to handle HDR from LDR inputs.
The authors tackled the problem of reconstructing high dynamic range (HDR) radiance fields from low dynamic range (LDR) images with varying exposures, enabling the generation of novel HDR and LDR views under different exposures. They validated their method on synthetic and real-world scenes, achieving accurate exposure control and high dynamic range rendering.
We present High Dynamic Range Neural Radiance Fields (HDR-NeRF) to recover an HDR radiance field from a set of low dynamic range (LDR) views with different exposures. Using the HDR-NeRF, we are able to generate both novel HDR views and novel LDR views under different exposures. The key to our method is to model the physical imaging process, which dictates that the radiance of a scene point transforms to a pixel value in the LDR image with two implicit functions: a radiance field and a tone mapper. The radiance field encodes the scene radiance (values vary from 0 to +infty), which outputs the density and radiance of a ray by giving corresponding ray origin and ray direction. The tone mapper models the mapping process that a ray hitting on the camera sensor becomes a pixel value. The color of the ray is predicted by feeding the radiance and the corresponding exposure time into the tone mapper. We use the classic volume rendering technique to project the output radiance, colors, and densities into HDR and LDR images, while only the input LDR images are used as the supervision. We collect a new forward-facing HDR dataset to evaluate the proposed method. Experimental results on synthetic and real-world scenes validate that our method can not only accurately control the exposures of synthesized views but also render views with a high dynamic range.