We present NeuralLabeling, a labeling approach and toolset for annotating 3D scenes using either bounding boxes or meshes and generating segmentation masks, affordance maps, 2D bounding boxes, 3D bounding boxes, 6DOF object poses, depth maps, and object meshes. NeuralLabeling uses Neural Radiance Fields (NeRF) as a renderer, allowing labeling to be performed using 3D spatial tools while incorporating geometric clues such as occlusions, relying only on images captured from multiple viewpoints as input. To demonstrate the applicability of NeuralLabeling to a practical problem in robotics, we added ground truth depth maps to 30000 frames of transparent object RGB and noisy depth maps of glasses placed in a dishwasher captured using an RGBD sensor, yielding the Dishwasher30k dataset. We show that training a simple deep neural network with supervision using the annotated depth maps yields a higher reconstruction performance than training with the previously applied weakly supervised approach. We also show how instance segmentation and depth completion datasets generated using NeuralLabeling can be incorporated into a robot application for grasping transparent objects placed in a dishwasher with an accuracy of 83.3%, compared to 16.3% without depth completion. Supplementary URI: https://florise.github.io/neural_labeling_web/.

We introduce Physically Enhanced Gaussian Splatting Simulation System (PEGASUS) for 6DoF object pose dataset generation, a versatile dataset generator based on 3D Gaussian Splatting. Environment and object representations can be easily obtained using commodity cameras to reconstruct with Gaussian Splatting. PEGASUS allows the composition of new scenes by merging the respective underlying Gaussian Splatting point cloud of an environment with one or multiple objects. Leveraging a physics engine enables the simulation of natural object placement within a scene through interaction between meshes extracted for the objects and the environment. Consequently, an extensive amount of new scenes - static or dynamic - can be created by combining different environments and objects. By rendering scenes from various perspectives, diverse data points such as RGB images, depth maps, semantic masks, and 6DoF object poses can be extracted. Our study demonstrates that training on data generated by PEGASUS enables pose estimation networks to successfully transfer from synthetic data to real-world data. Moreover, we introduce the Ramen dataset, comprising 30 Japanese cup noodle items. This dataset includes spherical scans that capture images from both the object hemisphere and the Gaussian Splatting reconstruction, making them compatible with PEGASUS.

We propose a technique for depth completion of transparent objects using augmented data captured directly from real environments with complicated geometry. Using cyclic adversarial learning we train translators to convert between painted versions of the objects and their real transparent counterpart. The translators are trained on unpaired data, hence datasets can be created rapidly and without any manual labeling. Our technique does not make any assumptions about the geometry of the environment, unlike SOTA systems that assume easily observable occlusion and contact edges, such as ClearGrasp. We show how our technique outperforms ClearGrasp in a dishwasher environment, in which occlusion and contact edges are difficult to observe. We also show how the technique can be used to create an object manipulation application with a humanoid robot. Supplementary URI: https://ftorise.github.io/faking_depth_web/.

Abstract Organizations are introducing agile and lean software development techniques in operations to increase the pace of their software development process and to improve the quality of their software. They use the term DevOps, a portmanteau of development and operations, as an umbrella term to describe their efforts. In this paper, we describe the ways in which organizations implement DevOps and the outcomes they experience. We first summarize the results of a systematic literature review that we performed to discover what researchers have written about DevOps. We then describe the results of an exploratory interview‐based study involving 6 organizations of various sizes that are active in various industries. As part of our findings, we observed that all organizations were positive about their experiences and only minor problems were encountered while adopting DevOps.

Software development can profit from improvements in the deployment and maintenance phases. DevOps improves these phases through a collection of principles and practices, centered around close collaboration between Development and Operations personnel. Both sides have paid little attention to issues faced by each other. Yet knowledge sharing is invaluable. Development personnel can for example make software more robust by implementing scalability and performance features desired by operations personnel.