Our HDR-NeRF is able to render novel HDR views. The tone-mapped HDR views reveal the details of over-exposure and under-exposure areas.

An end-to-end method HDR-NeRF is proposed to re- cover the high dynamic range neural radiance field from multiple LDR views with different amounts of exposure.

Nov 29, 2021 · 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 ...

We collect an HDR dataset (multi-view and multi-exposure) that contains 8 synthetic scenes rendered with Blender and 4 real scenes captured by a digital camera.

An end-to-end method HDR-NeRF is proposed to re- cover the high dynamic range neural radiance field from multiple LDR views with different amounts of exposure.

We propose a dynamic HDR NeRF framework, named as HDR-HexPlane, which can learn 3D scenes from dynamic 2D images captured with various exposures.

Therefore, we propose a novel method for recovering radiance fields from LDR views. Compared with HDR imaging+vanilla NeRF, our method is an end- to-end ...

We propose Instant High Dynamic Range Neural Radiance Fields (Instant HDR-NeRF), a method of learning high dynamic range (HDR) view synthesis from a set of ...

Apr 26, 2023 · A method that uses the photos with full dynamic range information from a HDR camera instead of stitching LDR photos of varying exposures like this method does.

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 simplified ...