
YW
Yinan Wang, Rohan Kadkol, Hyunjin Yoo, Jean-Fran\c{c}ois Lalonde, James J. Clark
· 1 min read
ResearcharXiv cs.CV
Multi-View Relighting with Mergeable Radiance Fields
arXiv:2611.25523v1 Announce Type: new
Abstract: We propose MergeableRF, a method for radiance field relighting through model parameter merging. Given multi-view images of a scene under known basis lights, our goal is to relight the scene by directly combining the parameters of radiance fields trained under these lights. This is motivated by the linearity of light transport: the image under a mixture of lights is the same weighted combination of the images under each light. However, combining the parameters of independently trained radiance fields does not produce the corresponding combination of images. To address this, we represent a scene with shared geometry and a separate appearance network for each basis light. We start these networks from the same initialization and introduce merge-aware training, which teaches their parameter combinations to reproduce the corresponding combinations of images. Given a target HDR environment map, we compute its basis-light coefficients and use them to merge the appearance networks into a single relit model. Our method supports both Neural Radiance Fields (NeRFs) and 3D Gaussian Splatting (3DGS), without material estimation, additional relighting networks, or target-specific optimization. Unlike image-space blending, it requires only one rendering pass per viewpoint. Experiments on synthetic Neural Gaffer objects and real OLATverse captures demonstrate relighting quality competitive with methods trained on the same multi-light observations.
Original source
This story was published by arXiv cs.CV and written by Yinan Wang, Rohan Kadkol, Hyunjin Yoo, Jean-Fran\c{c}ois Lalonde, James J. Clark. SyncAI.news shows a preview; the complete article is on the publisher's site.
Read the full story on arxiv.org


