We present a diverse dataset of industrial metal objects. These objects are symmetric, textureless and highly reflective, leading to challenging conditions not captured in existing datasets. Our dataset contains both real-world and synthetic multi-view RGB images with 6D object pose labels. Real-world data is obtained by recording multi-view images of scenes with varying object shapes, materials, carriers, compositions and lighting conditions. This results in over 30,000 images, accurately labelled using a new public tool. Synthetic data is obtained by carefully simulating realworld conditions and varying them in a controlled and realistic way. This leads to over 500,000 synthetic images. The close correspondence between synthetic and real-world data, and controlled variations, will facilitate sim-toreal research. Our dataset's size and challenging nature will facilitate research on various computer vision tasks involving reflective materials. The dataset and accompanying resources are made available on the project website https://pderoovere.github.io/dimo.

This paper presents the augmentation of immersive omnidirectional video with realistically lit objects. Recent years have known a proliferation of real-time capturing and rendering methods of omnidirectional video. Together with these technologies, rendering devices such as Oculus Rift have increased the immersive experience of users. We demonstrate the use of structure from motion on omnidirectional video to reconstruct the trajectory of the camera. The position of the car is then linked to an appropriate 360 • environment map. State-of-the-art augmented reality applications have often lacked realistic appearance and lighting. Our system is capable of evaluating the rendering equation in real-time, by using the captured omnidirectional video as a lighting environment. We demonstrate an application in which a computer generated vehicle can be controlled through an urban environment.

In this paper a deep learning architecture is presented that can, in real time, detect the 2D locations of certain landmarks of physical tools, such as a hammer or screwdriver. To avoid the labor of manual labeling, the network is trained on synthetically generated data. Training computer vision models on computer generated images, while still achieving good accuracy on real images, is a challenge due to the difference in domain. The proposed method uses an advanced rendering method in combination with transfer learning and an intermediate supervision architecture to address this problem. It is shown that the model presented in this paper, named Intermediate Heatmap Model (IHM), generalizes to real images when trained on synthetic data. To avoid the need for an exact textured 3D model of the tool in question, it is shown that the model will generalize to an unseen tool when trained on a set of different 3D models of the same type of tool. IHM is compared to two existing approaches to keypoint detection and it is shown that it outperforms those at detecting tool landmarks, trained on synthetic data.