The goal of this work is to perform 3D reconstruction and novel view synthesis from data captured by scanning platforms commonly deployed for world mapping in urban outdoor environments (e. g., Street View).
With only two training views on real-world images, DS-NeRF significantly outperforms NeRF as well as other sparse-view variants.
We present a framework for automatically reconfiguring images of street scenes by populating, depopulating, or repopulating them with objects such as pedestrians or vehicles.
Quantization is a key technique to reduce the resource requirement and improve the performance of neural network deployment.
Reduction in the cost of Network Cameras along with a rise in connectivity enables entities all around the world to deploy vast arrays of camera networks.
We introduce the problem of perpetual view generation - long-range generation of novel views corresponding to an arbitrarily long camera trajectory given a single image.
We propose a learning-based framework for disentangling outdoor scenes into temporally-varying illumination and permanent scene factors.
Cell-cell interactions have an integral role in tumorigenesis as they are critical in governing immune responses.
In this paper, we propose a learning algorithm for detecting visual image manipulations that is trained only using a large dataset of real photographs.