Skip to content

Implementation of the proposed ROS tool in the MLSP 2024 article "Photoconsistent and Trajectory Guided Novel-View Synthesis Tool for UAV Cinematography Based on Autoregressive Transformers"

Notifications You must be signed in to change notification settings

catec/nvs_trajectory_guided_ros

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Photoconsistent and Trajectory Guided Novel-View Synthesis Tool for UAV Cinematography Based on Autoregressive Transformers

Novel view synthesis is the task of generating new images that render an object or scene from a different viewpoint than the one given. It aims to create new views of a specific subject starting from a number of pictures taken from a known points of view. The novel view synthesis problem can be approached in two different ways: as a problem of interpolation of images between two known images or extrapolation of images from one or a subset of images. During this work, the problem of the extrapolation will be addressed. Taking advantage of the fact that it is possible to pre-calculate the trajectories that we want the camera that takes the images to execute, from a series of known shot-types. Based on that and on the Autoregressive Transformers, it is presented a end-to-end tool for novel-view synthesis from previously unvisited points of view for aerial cinematography robots.

proposed_tool_diagram


Repo content overview

It contains three main folders:

  • airsim_dataset_generator: It contains all the necessary tools for communicating with Airsim using Python as well as for generating trajectories or visualising them. This will simplify the task of generating datasets for computer vision.

  • proposed_tool: Contains the ROS nodes of the proposed tool.

Citation

Marco A. Montes-Grova, Vasileios Mygdalis, Francisco J. Pérez-Grau, Antidio Viguria and Ioannis Pitas. ICUAS 2024. "Photoconsistent and Trajectory Guided Novel-View Synthesis Tool for UAV Cinematography Based on Autoregressive Transformer". UNDER REVISION

If you use this data for any academic work, please cite our original paper: TBD

UNDER REVISION

Funding


AI4MEDIA

Supported by AI4MEDIA - A European Excellence Centre for Media, Society and Democracy. More information: ai4media.eu

eu_flag

This project has received funding from the European Union's Horizon 2020
research and innovation programme under grant agreement 951911.

About

Implementation of the proposed ROS tool in the MLSP 2024 article "Photoconsistent and Trajectory Guided Novel-View Synthesis Tool for UAV Cinematography Based on Autoregressive Transformers"

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages