Reconstructing dynamic scenes with commodity depth cameras has many applications in computer graphics, computer vision, and robotics. However, due to the presence of noise and erroneous observations from data capturing devices and the inherently ill-posed nature of non-rigid registration with insufficient information, traditional approaches often produce low-quality geometry with holes, bumps, and misalignments. We propose a novel 3D dynamic reconstruction system, named HDR-Net-Fusion, which learns to simultaneously reconstruct and refine the geometry on the fly with a sparse embedded deformation graph of surfels, using a hierarchical deep reinforcement (HDR) network. The latter comprises two parts: a global HDR-Net which rapidly detects local regions with large geometric errors, and a local HDR-Net serving as a local patch refinement operator to promptly complete and enhance such regions. Training the global HDR-Net is formulated as a novel reinforcement learning problem to implicitly learn the region selection strategy with the goal of improving the overall reconstruction quality. The applicability and efficiency of our approach are demonstrated using a large-scale dynamic reconstruction dataset. Our method can reconstruct geometry with higher quality than traditional methods.

We present a practical backend for stereovisual SLAM which can simultaneously discoverindividual rigid bodies and compute their motions in dynamic environments. While recent factor graph based state optimization algorithms have shown their ability to robustly solve SLAM problems by treating dynamic objects as outliers, their dynamic motions are rarely considered. In this paper, we exploit the consensus of 3D motions for landmarks extracted from the same rigid body for clustering, and to identify static and dynamic objects in a unified manner. Specifically, our algorithm builds a noise-aware motion affinity matrix from landmarks, and uses agglomerative clustering to distinguish rigid bodies. Using decoupled factor graph optimization to revise their shapes and trajectories, we obtain an iterative scheme to update both cluster assignments and motion estimation reciprocally. Evaluations on both synthetic scenes and KITTI demonstrate the capability of our approach, and further experiments considering online efficiency also show the effectiveness of our method for simultaneously tracking ego-motion and multiple objects.

Modeling the complete geometry of general shapes from a single image is an ill-posed problem. User hints are often incorporated to resolve ambiguities and provide guidance during the modeling process. In this work, we present a novel interactive approach for extracting high-quality freeform shapes from a single image. This is inspired by the popular lofting technique in many CAD systems, and only requires minimal user input. Given an input image, the user only needs to sketch several projected cross sections, provide a "main axis" , and specify some geometric relations. Our algorithm then automatically optimizes the common normal to the sections with respect to these constraints, and interpolates between the sections, resulting in a high-quality 3D model that conforms to both the original image and the user input. The entire modeling session is efficient and intuitive. We demonstrate the effectiveness of our approach based on qualitative tests on a variety of images, and quantitative comparisons with the ground truth using synthetic images.

The perception of the visual world through basic building blocks, such as cubes, spheres, and cones, gives human beings a parsimonious understanding of the visual world. Thus, efforts to find primitive-based geometric interpretations of visual data date back to 1970s studies of visual media. However, due to the difficulty of primitive fitting in the pre-deep learning age, this research approach faded from the main stage, and the vision community turned primarily to semantic image understanding. In this paper, we revisit the classical problem of building geometric interpretations of images, using supervised deep learning tools. We build a framework to detect primitives from images in a layered manner by modifying the YOLO network; an RNN with a novel loss function is then used to equip this network with the capability to predict primitives with a variable number of parameters. We compare our pipeline to traditional and other baseline learning methods, demonstrating that our layered detection model has higher accuracy and performs better reconstruction.