Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. Applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of structured da
ta. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes raw point clouds as input. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on multiple datasets where our method achieves state-of-the-art performance. We also extend and evaluate our network for instance and dynamic object segmentation.
Multi-View Stereo (MVS) is a core task in 3D computer vision. With the surge of novel deep learning methods, learned MVS has surpassed the accuracy of classical approaches, but still relies on building a memory intensive dense cost volume. Novel View
Synthesis (NVS) is a parallel line of research and has recently seen an increase in popularity with Neural Radiance Field (NeRF) models, which optimize a per scene radiance field. However, NeRF methods do not generalize to novel scenes and are slow to train and test. We propose to bridge the gap between these two methodologies with a novel network that can recover 3D scene geometry as a distance function, together with high-resolution color images. Our method uses only a sparse set of images as input and can generalize well to novel scenes. Additionally, we propose a coarse-to-fine sphere tracing approach in order to significantly increase speed. We show on various datasets that our method reaches comparable accuracy to per-scene optimized methods while being able to generalize and running significantly faster.
Modern rendering libraries provide unprecedented realism, producing real-time photorealistic 3D graphics on commodity hardware. Visual fidelity, however, comes at the cost of increased complexity and difficulty of usage, with many rendering parameter
s requiring a deep understanding of the pipeline. We propose EasyPBR as an alternative rendering library that strikes a balance between ease-of-use and visual quality. EasyPBR consists of a deferred renderer that implements recent state-of-the-art approaches in physically based rendering. It offers an easy-to-use Python and C++ interface that allows high-quality images to be created in only a few lines of code or directly through a graphical user interface. The user can choose between fully controlling the rendering pipeline or letting EasyPBR automatically infer the best parameters based on the current scene composition. The EasyPBR library can help the community to more easily leverage the power of current GPUs to create realistic images. These can then be used as synthetic data for deep learning or for creating animations for academic purposes.
Pose estimation and map building are central ingredients of autonomous robots and typically rely on the registration of sensor data. In this paper, we investigate a new metric for registering images that builds upon on the idea of the photometric err
or. Our approach combines a gradient orientation-based metric with a magnitude-dependent scaling term. We integrate both into stereo estimation as well as visual odometry systems and show clear benefits for typical disparity and direct image registration tasks when using our proposed metric. Our experimental evaluation indicats that our metric leads to more robust and more accurate estimates of the scene depth as well as camera trajectory. Thus, the metric improves camera pose estimation and in turn the mapping capabilities of mobile robots. We believe that a series of existing visual odometry and visual SLAM systems can benefit from the findings reported in this paper.
Deep convolutional neural networks (CNNs) have shown outstanding performance in the task of semantically segmenting images. However, applying the same methods on 3D data still poses challenges due to the heavy memory requirements and the lack of stru
ctured data. Here, we propose LatticeNet, a novel approach for 3D semantic segmentation, which takes as input raw point clouds. A PointNet describes the local geometry which we embed into a sparse permutohedral lattice. The lattice allows for fast convolutions while keeping a low memory footprint. Further, we introduce DeformSlice, a novel learned data-dependent interpolation for projecting lattice features back onto the point cloud. We present results of 3D segmentation on various datasets where our method achieves state-of-the-art performance.
Scene understanding is an important capability for robots acting in unstructured environments. While most SLAM approaches provide a geometrical representation of the scene, a semantic map is necessary for more complex interactions with the surroundin
gs. Current methods treat the semantic map as part of the geometry which limits scalability and accuracy. We propose to represent the semantic map as a geometrical mesh and a semantic texture coupled at independent resolution. The key idea is that in many environments the geometry can be greatly simplified without loosing fidelity, while semantic information can be stored at a higher resolution, independent of the mesh. We construct a mesh from depth sensors to represent the scene geometry and fuse information into the semantic texture from segmentations of individual RGB views of the scene. Making the semantics persistent in a global mesh enables us to enforce temporal and spatial consistency of the individual view predictions. For this, we propose an efficient method of establishing consensus between individual segmentations by iteratively retraining semantic segmentation with the information stored within the map and using the retrained segmentation to re-fuse the semantics. We demonstrate the accuracy and scalability of our approach by reconstructing semantic maps of scenes from NYUv2 and a scene spanning large buildings.
