Estimating depth from images nowadays yields outstanding results, both in terms of in-domain accuracy and generalization. However, we identify two main challenges that remain open in this field: dealing with non-Lambertian materials and effectively processing high-resolution images. Purposely, we propose a novel dataset that includes accurate and dense ground-truth labels at high resolution, featuring scenes containing several specular and transparent surfaces. Our acquisition pipeline leverages a novel deep space-time stereo framework, enabling easy and accurate labeling with sub-pixel precision. The dataset is composed of 606 samples collected in 85 different scenes, each sample includes both a high-resolution pair (12 Mpx) as well as an unbalanced stereo pair (Left: 12 Mpx, Right: 1.1 Mpx), typical of modern mobile devices that mount sensors with different resolutions. Additionally, we provide manually annotated material segmentation masks and 15K unlabeled samples. The dataset is composed of a train set and two test sets, the latter devoted to the evaluation of stereo and monocular depth estimation networks. Our experiments highlight the open challenges and future research directions in this field.
Learning to Remove Wrinkled Transparent Film with Polarized Prior
The Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；SmartMore Corporation（旷世科技公司）；Zhejiang University（浙江大学）；Zhejiang Lab（浙江大学实验室）
We present a novel high-resolution and challenging stereo dataset framing indoor scenes annotated with dense and accurate ground-truth disparities. Peculiar to our dataset is the presence of several specular and transparent surfaces, i.e. the main causes of failures for state-of-the-art stereo networks. Our acquisition pipeline leverages a novel deep space-time stereo framework which allows for easy and accurate labeling with sub-pixel precision. We release a total of 419 samples collected in 64 different scenes and annotated with dense ground-truth disparities. Each sample include a high-reso…
Commercial depth sensors usually generate noisy and missing depths, especially on specular and transparent objects, which poses critical issues to downstream depth or point cloud-based tasks. To mitigate this problem, we propose a powerful RGBD fusion network, SwinDRNet, for depth restoration. We further propose Domain Randomization-Enhanced Depth Simulation (DREDS) approach to simulate an active stereo depth system using physically based rendering and generate a large-scale synthetic dataset that contains 130K photorealistic RGB images along with their simulated depths carrying realistic sens…
Transparent objects present multiple distinct challenges to visual perception systems. First, their lack of distinguishing visual features makes transparent objects harder to detect and localize than opaque objects. Even humans find certain transparent surfaces with little specular reflection or refraction, e.g. glass doors, difficult to perceive. A second challenge is that common depth sensors typically used for opaque object perception cannot obtain accurate depth measurements on transparent objects due to their unique reflective properties. Stemming from these challenges, we observe that tr…
GAA-TSO: Geometry-Aware Assisted Depth Completion for Transparent and Specular Objects
College of Information Science and Engineering, Northeastern University（东北大学信息科学与工程学院）；National Frontiers Science Center for Industrial Intelligence and Systems Optimization（工业智能与系统优化国家前沿科学中心）
SR3D: Unleashing Single-view 3D Reconstruction for Transparent and Specular Object Grasping
Beijing University of Posts and Telecommunications（北京邮电大学）；Center on Frontiers of Computing Studies, Peking University（北京大学前沿计算研究中心）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）
Peking University（北京大学）；National University of Defense Technology（国防科技大学）；Beijing Academy of Artificial Intelligence（北京人工智能研究院）
In this work, we tackle 6-DoF grasp detection for transparent and specular objects, which is an important yet challenging problem in vision-based robotic systems, due to the failure of depth cameras in sensing their geometry. We, for the first time, propose a multiview RGB-based 6-DoF grasp detection network, GraspNeRF, that leverages the generalizable neural radiance field (NeRF) to achieve material-agnostic object grasping in clutter. Compared to the existing NeRF-based 3-DoF grasp detection methods that rely on densely captured input images and time-consuming per-scene optimization, our sys…
Massachusetts Institute of Technology（麻省理工学院）；The Charles Stark Draper Laboratory（查尔斯·斯塔克·德雷珀实验室）
We propose methods that use specular, multibounce lidar returns to detect and map specular surfaces that might be invisible to conventional lidar systems that rely on direct, single-scatter returns. We derive expressions that relate the time- and angle-of-arrival of these multibounce returns to scattering points on the specular surface, and then use these expressions to formulate techniques for retrieving specular surface geometry when the scene is scanned by a single beam or illuminated with a multi-beam flash. We also consider the special case of transparent specular surfaces, for which surf…
The ability to grasp and manipulate transparent objects is a major challenge for robots. Existing depth cameras have difficulty detecting, localizing, and inferring the geometry of such objects. We propose using neural radiance fields (NeRF) to detect, localize, and infer the geometry of transparent objects with sufficient accuracy to find and grasp them securely. We leverage NeRF's view-independent learned density, place lights to increase specular reflections, and perform a transparency-aware depth-rendering that we feed into the Dex-Net grasp planner. We show how additional lights create sp…
We present a large-scale stereo RGB image object pose estimation dataset named the $\textbf{StereOBJ-1M}$ dataset. The dataset is designed to address challenging cases such as object transparency, translucency, and specular reflection, in addition to the common challenges of occlusion, symmetry, and variations in illumination and environments. In order to collect data of sufficient scale for modern deep learning models, we propose a novel method for efficiently annotating pose data in a multi-view fashion that allows data capturing in complex and flexible environments. Fully annotated with 6D …
A reliable stereo algorithm is critical for many robotics applications. But textureless and specular regions can easily cause failure by making feature matching difficult. Understanding whether an algorithm is robust to these hazardous regions is important. Although many stereo benchmarks have been developed to evaluate performance, it is hard to quantify the effect of hazardous regions in real images because the location and severity of these regions are unknown. In this paper, we develop a synthetic image generation tool enabling to control hazardous factors, such as making objects more spec…
Geometry Reinforced Efficient Attention Tuning Equipped with Normals for Robust Stereo Matching
Department of Computer Science, City University of Hong Kong（香港城市大学计算机科学系）；Department of Computer Science, Southern Methodist University（南卫理公会大学计算机科学系）；Hon Hai Research Institute（鸿海研究院）
ASGrasp: Generalizable Transparent Object Reconstruction and 6-DoF Grasp Detection from RGB-D Active Stereo Camera
Samsung R&D Institute China-Beijing（三星中国北京研发中心）；CFCS, School of Computer Science, Peking University（计算机科学系，北京大学）；Beijing Academy of Artificial Intelligence (BAAI)（北京人工智能研究院）
Real-Time Glass Detection and Reprojection using Sensor Fusion Onboard Aerial Robots
ARL DCIST CRA；NSF Grant CCR-2112665（NSF CCR-2112665）；NSF Graduate Research Fellowship Grant No. DGE-1845298（NSF DGE-1845298）；IoT4Ag Engineering Research Center
AISPO: Enhancing Depth Reliability for Robotic Manipulation of Non-Lambertian Objects via Affine-Invariant Shape Prior
The Hong Kong University of Science & Technology（香港科技大学）；The University of Hong Kong（香港大学）；Southern University of Science & Technology（南方科技大学）；Zhejiang University（浙江大学）；LimX Dynamics
Towards Robust Monocular Depth Estimation in Non-Lambertian Surfaces
School of Future Technology, Huazhong University of Science and Technology（华中科技大学未来技术学院）；School of AIA, Huazhong University of Science and Technology（华中科技大学AIA学院）
