Temporally Consistent Depth Prediction Enabled by a Multi-Task Geometric and Semantic Scene Understanding Approach [Neural Network Weights]

Actions

This file is not currently in any collections.

Resource type: Other
Contributors: Creator: Atapour-Abarghouei, Amir ¹
Contact person: Atapour-Abarghouei, Amir ¹
Editor: Atapour-Abarghouei, Amir ¹
Contact person: Breckon, Toby P. ¹
Editor: Breckon, Toby P. ¹

¹ Durham University, UK
Funder
Research methods
Other description: The data file has been created using PyTorch ( https://pytorch.org
) and contains the weights of a generative model trained to perform monocular depth estimation and semantic segmentation. The file is needed as part of the pipeline for the project at https://github.com/atapour/temporal-depth-segmentation
Instructions on how the file can be used and how the code is run can also be found at https://github.com/atapour/temporal-depth-segmentation
Keyword: Monocular Depth Estimation
Semantic Segmentation
Temporal Consistency
Computer Vision
Subject
Location
Language
Cited in
Identifier: ark:/32150/r25425k9734
Rights: MIT Licence (MIT)
Publisher: Durham University
Date Created

Depositor: A. Atapour Abarghouei
Date Uploaded: 15 March 2019, 12:03:16
Date Modified: 18 March 2019, 11:03:17
Audit Status: Audits have not yet been run on this file.
Characterization: File format: zip (ZIP Format)

Mime type: application/zip

File size: 539415560

Last modified: 2019:03:15 12:30:46+00:00

Filename: pre_trained_weights.zip

Original checksum: e955db2cf2bc11a3e79e2d2153299fce

Activity of users you follow
User Activity	Date