AtLoc: Attention Guided Camera Localization
Authors: Bing Wang, Changhao Chen, Chris Xiaoxuan Lu, Peijun Zhao, Niki Trigoni, Andrew Markham10393-10401
AAAI 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Extensive experimental evidence is provided through public indoor and outdoor datasets. Through visualization of the saliency maps, we demonstrate how the network learns to reject dynamic objects, yielding superior global camera pose regression performance. Through extensive experiments in both indoor and outdoor scenarios, we show that our model achieves state-of-the-art performance in pose regression, even outperforming multiple frame (sequential) methods. |
| Researcher Affiliation | Academia | Bing Wang, Changhao Chen,* Chris Xiaoxuan Lu, Peijun Zhao, Niki Trigoni, Andrew Markham Department of Computer Science, University of Oxford firstname.lastname@cs.ox.ac.uk |
| Pseudocode | No | The paper describes the model components and mathematical formulations (e.g., equations 1-9) but does not include any structured pseudocode or algorithm blocks. |
| Open Source Code | Yes | The source code is avaliable at https://github.com/Bing CS/At Loc. |
| Open Datasets | Yes | 7 Scenes (Shotton et al. 2013) is a dataset consisting of RGB-D images from seven different indoor scenes captured by a handheld Kinect RGB-D camera. Oxford Robot Car (Maddern et al. 2017) was recorded by an autonomous Nissan LEAF car in Oxford, UK over several periods for a year. |
| Dataset Splits | Yes | Each scene contains two to seven sequences in a single room for training/testing, with 500 or 1000 images for each sequence. For a fair comparison, we follow the same evaluation strategy of Map Net (Brahmbhatt et al. 2018; Xue et al. 2019) and use two subsets of this dataset in our experiments, labelled as LOOP and FULL (length-based) Sequence Time Tag Mode 2014-06-26-08-53-56 overcast Training 2014-06-26-09-24-58 overcast Training LOOP1 2014-06-23-15-41-25 sunny Testing LOOP2 2014-06-23-15-36-04 sunny Testing... |
| Hardware Specification | Yes | The network is trained on a NVIDIA Titan X GPU with the following hyperparameters: mini-batch size of 64, dropout rate probability of 0.5 and weight initializations of β0 = 0.0 and γ0 = 3.0. |
| Software Dependencies | No | We implement our approaches with Py Torch, using the ADAM solver (Kingma and Ba 2014) and an initial learning rate of 5 10 5. |
| Experiment Setup | Yes | We implement our approaches with Py Torch, using the ADAM solver (Kingma and Ba 2014) and an initial learning rate of 5 10 5. The network is trained on a NVIDIA Titan X GPU with the following hyperparameters: mini-batch size of 64, dropout rate probability of 0.5 and weight initializations of β0 = 0.0 and γ0 = 3.0. When introducing temporal constraints, we sample consecutive triplets every 10 frames with α0 = 1.0 and initialize weight coefficient α0 = 1.0. |