In this paper, we introduce the first framework that enables users to remove unwanted objects or retouch undesired regions in a 3D scene represented by a pre-trained NeRF without any category-specific data and training.
This paper proposes a robust localization system that employs deep learning for better scene representation, and enhances the accuracy of 6-DOF camera pose estimation.
In the past few years, deep reinforcement learning has been proven to solve problems which have complex states like video games or board games.
Automatic photo cropping is an important tool for improving visual quality of digital photos without resorting to tedious manual selection.
In this paper, an inter-video mapping approach is proposed to integrate video footages from two dashcams installed on a preceding and its following vehicle to provide the illusion that the driver of the following vehicle can see-through the preceding one.
Inspired by the observation that the homographies of correct feature correspondences vary smoothly along the spatial domain, our approach stands on the unsupervised nature of feature matching, and can select a good descriptor for matching each feature point.
Inspired by the fact that nearby features on the same object share coherent homographies in matching, we cast the task of feature matching as a density estimation problem in the Hough space spanned by the hypotheses of homographies.