Search Results for author:
Found 4 papers, 2 papers with code
ManifoldNeRF: View-dependent Image Feature Supervision for Few-shot Neural Radiance Fields
DietNeRF is an extension of NeRF that aims to achieve this task from only a few images by introducing a new loss function for unknown viewpoints with no input images.
Dehazing Cost Volume for Deep Multi-view Stereo in Scattering Media with Airlight and Scattering Coefficient Estimation
We also propose a method of estimating scattering parameters, such as airlight, and a scattering coefficient, which are required for our dehazing cost volume.
Partially-Shared Variational Auto-encoders for Unsupervised Domain Adaptation with Target Shift
In practice, this is an important problem in UDA; as we do not know labels in target domain datasets, we do not know whether or not its distribution is identical to that in the source domain dataset.
Defogging Kinect: Simultaneous Estimation of Object Region and Depth in Foggy Scenes
The scattering component is saturated, so it does not depend on the scene depth, and received signals bouncing off distant points are negligible due to light attenuation in the participating media, so the observation of such a point contains only a scattering component.
