pith. sign in

arxiv: 2312.14235 · v1 · pith:FUNFI2RInew · submitted 2023-12-21 · 💻 cs.CV

Neural Spline Fields for Burst Image Fusion and Layer Separation

classification 💻 cs.CV
keywords imageburstobstructionsplineablecomplexfieldslayer
0
0 comments X
read the original abstract

Each photo in an image burst can be considered a sample of a complex 3D scene: the product of parallax, diffuse and specular materials, scene motion, and illuminant variation. While decomposing all of these effects from a stack of misaligned images is a highly ill-conditioned task, the conventional align-and-merge burst pipeline takes the other extreme: blending them into a single image. In this work, we propose a versatile intermediate representation: a two-layer alpha-composited image plus flow model constructed with neural spline fields -- networks trained to map input coordinates to spline control points. Our method is able to, during test-time optimization, jointly fuse a burst image capture into one high-resolution reconstruction and decompose it into transmission and obstruction layers. Then, by discarding the obstruction layer, we can perform a range of tasks including seeing through occlusions, reflection suppression, and shadow removal. Validated on complex synthetic and in-the-wild captures we find that, with no post-processing steps or learned priors, our generalizable model is able to outperform existing dedicated single-image and multi-view obstruction removal approaches.

This paper has not been read by Pith yet.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.