In man-made environments such as indoor scenes, when point-based 3D reconstruction fails due to the lack of texture, lines can still be detected and used to support surfaces. We present a novel method for watertight piecewise-planar surface reconstruction from 3D line segments with visibility information. First, planes are extracted by a novel RANSAC approach for line segments that allows multiple shape support. Then, each 3D cell of a plane arrangement is labeled full or empty based on line attachment to planes, visibility and regularization. Experiments show the robustness to sparse input data, noise and outliers.

Most deep pose estimation methods need to be trained for specific object instances or categories. In this work we propose a completely generic deep pose estimation approach, which does not require the network to have been trained on relevant categories, nor objects in a category to have a canonical pose. We believe this is a crucial step to design robotic systems that can interact with new objects "in the wild" not belonging to a predefined category. Our main insight is to dynamically condition pose estimation with a representation of the 3D shape of the target object. More precisely, we train a Convolutional Neural Network that takes as input both a test image and a 3D model, and outputs the relative 3D pose of the object in the input image with respect to the 3D model. We demonstrate that our method boosts performances for supervised category pose estimation on standard benchmarks, namely Pascal3D+, ObjectNet3D and Pix3D, on which we provide results superior to the state of the art. More importantly, we show that our network trained on everyday man-made objects from ShapeNet generalizes without any additional training to completely new types of 3D objects by providing results on the LINEMOD dataset as well as on natural entities such as animals from ImageNet. Our code and model is avalaible at http://imagine.enpc.fr/~xiaoy/PoseFromShape/.

No abstract

3D scene reconstruction has important applications to help to produce digital twins of existing buildings. While the community has mostly focused on surface reconstruction or semantic segmentation as separate problems, the joint reconstruction of both volumes and semantics has little been discussed, mostly due to the lack of large scale volume datasets with semantic annotations. In this work, we introduce a new dataset called VASAD for Volume And Semantic Architectural Dataset. It is composed of 6 building models, with full volume description and semantic labels. It approximately represents 62,000 m 2 of building floors, making it large enough for the development and evaluation of learning-based approaches. We propose several methods to jointly reconstruct both geometry and semantics and evaluate on the test set of the dataset. We show that the proposed dataset is challenging enough to stimulate research. The dataset is available at https://github.com/palanglois/vasad.

The top-down cracking of asphalt concrete pavements caused by thermal factors are very common in Poland. Cracking can occur as a result of a single intensive event (severe temperature drop) or as a result of cyclic long-term less severe events (thermal fatigue).In both cases precise constitutive modeling of materials is a key issue for rational prediction of the pavement behavior. As a starting point the Thermal Stress Restrained Specimen Test (TSRST) in which the shrinkage proceeds due to temperature reduction is analyzed and compared with experiment results for chosen mix. The TSRST is modeled using the finite element method in a frame of thermo-mechanics with the so-called weak coupling between thermal and mechanical effects. Mechanical properties are taken into account by the constitutive relations of elasticity, visco-elasticity and continuum cracking models. Among the continuum cracking models special place is devoted to cohesive zone model which is a new development in fracture mechanics. Cohesive zone model in many works is presented as the only solution for rational modeling of TSRST and this notion is also addressed herein.

There has been recently a growing interest for implicit shape representations. Contrary to explicit representations, they have no resolution limitations and they easily deal with a wide variety of surface topologies. To learn these implicit representations, current approaches rely on a certain level of shape supervision (e.g., inside/outside information or distance-to-shape knowledge), or at least require a dense point cloud (to approximate well enough the distance-to-shape). In contrast, we introduce NeeDrop, an self-supervised method for learning shape representations from possibly extremely sparse point clouds. Like in Buffon's needle problem, we "drop" (sample) needles on the point cloud and consider that, statistically, close to the surface, the needle end points lie on opposite sides of the surface. No shape knowledge is required and the point cloud can be highly sparse, e.g., as lidar point clouds acquired by vehicles. Previous self-supervised shape representation approaches fail to produce good-quality results on this kind of data. We obtain quantitative results on par with existing supervised approaches on shape reconstruction datasets and show promising qualitative results on hard autonomous driving datasets such as KITTI.

We introduce an approach for computing a 3D mesh from one or more views of an object by establishing dense correspondences between pixels in the views and 3D locations on a learnable parameterized surface. We propose a multi-view shape encoder that can be jointly trained with the AtlasNet surface parameterization. The shape is further refined using a novel geometric cycle-consistency loss between the learnable parameterized surface and input views. We demonstrate the efficacy of our approach on the ShapeNet-COCO dataset.