In this work, we propose HyperPose, which utilizes hypernetworks in absolute camera pose regressors. The inherent appearance variations in natural scenes, attributable to environmental conditions, perspective, and lighting, induce a significant domain disparity between the training and test datasets. This disparity degrades the precision of contemporary localization networks. To mitigate this, we advocate for incorporating hypernetworks into single-scene and multiscene camera pose regression models. During inference, the hypernetwork dynamically computes adaptive weights for the localization regression heads based on the particular input image, effectively narrowing the domain gap. Using indoor and outdoor datasets, we evaluate the HyperPose methodology across multiple established absolute pose regression architectures. We also introduce and share the Extended Cambridge Landmarks (ECL), a novel localization dataset, based on the Cambridge Landmarks dataset, showing it in multiple seasons with significantly varying appearance conditions. Our empirical experiments demonstrate that HyperPose yields notable performance enhancements for single- and multi-scene architectures. We have made our source code, pre-trained models1, and the ECL dataset openly available2.

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 self-attention 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 Shavit et al. (2021) by introducing a mixed classification-regression 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.

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 using 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 https://github.com/yolish/multi-scene-pose-transformer.

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.

We explore the feasibility of measuring learner engagement and classifying the engagement level based on machine learning applied on data from 2D/3D camera sensors and eye trackers in a 1:1 learning setting. Our results are based on nine pilot sessions held in a local high school where we recorded features related to student engagement while consuming educational content. We label the collected data as Engaged or NotEngaged while observing videos of the students and their screens. Based on the collected data, perceptual user features (e.g., body posture, facial points, and gaze) are extracted. We use feature selection and classification methods to produce classifiers that can detect whether a student is engaged or not. Accuracies of up to 85-95% are achieved on the collected dataset. We believe our work pioneers in the successful classification of student engagement based on perceptual user features in a 1:1 authentic learning setting.