Absolute camera pose regressors estimate the position and orientation of a camera given the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron (MLP) head is trained using images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended to learn multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with selfattention and decoders transform latent features and scenes encoding into pose predictions. This allows our model to focus on general features that are informative for localization, while embedding multiple scenes in parallel. We extend our previous MS-Transformer approach [1] by introducing a mixed classificationregression architecture that improves the localization accuracy. Our method is evaluated on commonly benchmark indoor and outdoor datasets and has been shown to exceed both multi-scene and state-of-the-art single-scene absolute pose regressors. We make our code publicly available from here.
Visual pose regression models estimate the camera pose from a query image with a single forward pass. Current models learn pose encoding from an image using deep convolutional networks which are trained per scene. The resulting encoding is typically passed to a multi-layer perceptron in order to regress the pose. In this work, we propose that scene-specific pose encoders are not required for pose regression and that encodings trained for visual similarity can be used instead. In order to test our hypothesis, we take a shallow architecture of several fully connected layers and train it with pre-computed encodings from a generic image retrieval model. We find that these encodings are not only sufficient to regress the camera pose, but that, when provided to a branching fully connected architecture, a trained model can achieve competitive results and even surpass current state-of-the-art pose regressors in some cases. Moreover, we show that for outdoor localization, the proposed architecture is the only pose regressor, to date, consistently localizing in under 2 meters and 5 degrees.
Absolute camera pose regressors estimate the position and orientation of a camera from the captured image alone. Typically, a convolutional backbone with a multi-layer perceptron head is trained with images and pose labels to embed a single reference scene at a time. Recently, this scheme was extended for learning multiple scenes by replacing the MLP head with a set of fully connected layers. In this work, we propose to learn multi-scene absolute camera pose regression with Transformers, where encoders are used to aggregate activation maps with self-attention and decoders transform latent features and scenes encoding into candidate pose predictions. This mechanism allows our model to focus on general features that are informative for localization while embedding multiple scenes in parallel. We evaluate our method on commonly benchmarked indoor and outdoor datasets and show that it surpasses both multi-scene and state-of-the-art single-scene absolute pose regressors. We make our code publicly available from here.
The proposed attention-based regression localization scheme. The input image is first encoded by a convolutional backbone. Two activation maps, at different resolutions, are transformed into sequential representations. The two activation sequences are analyzed by dual Transformer encoders, one per regression task. We depict the attention weights via heatmaps. Position is best estimated by corner-like image features, while orientation is estimated by edge-like features. Each Transformer encoder output is used to regress the respective camera pose component (position x or orientation q).
In this study, we propose the use of attention hypernetworks in camera pose localization. The dynamic nature of natural scenes, including changes in environment, perspective, and lighting, creates an inherent domain gap between the training and test sets that limits the accuracy of contemporary localization networks. To overcome this issue, we suggest a camera pose regressor that integrates a hypernetwork. During inference, the hypernetwork generates adaptive weights for the localization regression heads based on the input image, effectively reducing the domain gap. We also suggest the use of a Transformer-Encoder as the hypernetwork, instead of the common multilayer perceptron, to derive an attention hypernetwork. The proposed approach achieves superior results compared to state-of-the-art methods on contemporary datasets. To the best of our knowledge, this is the first instance of using hypernetworks in camera pose regression, as well as using Transformer-Encoders as hypernetworks. We make our code publicly available 1 .
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.