Chul Min Yeum

Hansol Lim, Hanbeom Chang, Jongseong Brad Choi et al.

In this paper, we explore the capabilities of multimodal inputs to 3D Gaussian Splatting (3DGS) based Radiance Field Rendering. We present LiDAR-3DGS, a novel method of reinforcing 3DGS inputs with LiDAR generated point clouds to significantly improve the accuracy and detail of 3D models. We demonstrate a systematic approach of LiDAR reinforcement to 3DGS to enable capturing of important features such as bolts, apertures, and other details that are often missed by image-based features alone. These details are crucial for engineering applications such as remote monitoring and maintenance. Without modifying the underlying 3DGS algorithm, we demonstrate that even a modest addition of LiDAR generated point cloud significantly enhances the perceptual quality of the models. At 30k iterations, the model generated by our method resulted in an increase of 7.064% in PSNR and 0.565% in SSIM, respectively. Since the LiDAR used in this research was a commonly used commercial-grade device, the improvements observed were modest and can be further enhanced with higher-grade LiDAR systems. Additionally, these improvements can be supplementary to other derivative works of Radiance Field Rendering and also provide a new insight for future LiDAR and computer vision integrated modeling.

Josh Qixuan Sun, Xiaoying Xing, Huaiyuan Weng et al.

Vision-Language Navigation in Continuous Environments (VLNCE), where an agent follows instructions and moves freely to reach a destination, is a key research problem in embodied AI. However, most navigation policies are sensitive to viewpoint changes, i.e., variations in camera height and viewing angle that alter the agent's observation. In this paper, we introduce a generalized scenario, V2-VLNCE (VLNCE with Varied Viewpoints), and propose VIL (View Invariant Learning), a view-invariant post-training strategy that enhances the robustness of existing navigation policies to changes in camera viewpoint. VIL employs a contrastive learning framework to learn sparse and view-invariant features. Additionally, we introduce a teacher-student framework for the Waypoint Predictor Module, a core component of most VLNCE baselines, where a view-dependent teacher model distills knowledge into a view-invariant student model. We employ an end-to-end training paradigm to jointly optimize these components, thus eliminating the cost for individual module training. Empirical results show that our method outperforms state-of-the-art approaches on V2-VLNCE by 8-15% measured on Success Rate for two standard benchmark datasets R2R-CE and RxR-CE. Furthermore, we evaluate VIL under the standard VLNCE setting and find that, despite being trained for varied viewpoints, it often still improves performance. On the more challenging RxR-CE dataset, our method also achieved state-of-the-art performance across all metrics when compared to other map-free methods. This suggests that adding VIL does not diminish the standard viewpoint performance and can serve as a plug-and-play post-training method.

Hanbeom Chang, Jongseong Brad Choi, Chul Min Yeum

Indoor SLAM often suffers from issues such as scene drifting, double walls, and blind spots, particularly in confined spaces with objects close to the sensors (e.g. LiDAR and cameras) in reconstruction tasks. Real-time visualization of point cloud registration during data collection may help mitigate these issues, but a significant limitation remains in the inability to in-depth compare the scanned data with actual physical environments. These challenges obstruct the quality of reconstruction products, frequently necessitating revisit and rescan efforts. For this regard, we developed the LiMRSF (LiDAR-MR-RGB Sensor Fusion) system, allowing users to perceive the in-situ point cloud registration by looking through a Mixed-Reality (MR) headset. This tailored framework visualizes point cloud meshes as holograms, seamlessly matching with the real-time scene on see-through glasses, and automatically highlights errors detected while they overlap. Such holographic elements are transmitted via a TCP server to an MR headset, where it is calibrated to align with the world coordinate, the physical location. This allows users to view the localized reconstruction product instantaneously, enabling them to quickly identify blind spots and errors, and take prompt action on-site. Our blind spot detector achieves an error detection precision with an F1 Score of 75.76% with acceptably high fidelity of monitoring through the LiMRSF system (highest SSIM of 0.5619, PSNR of 14.1004, and lowest MSE of 0.0389 in the five different sections of the simplified mesh model which users visualize through the LiMRSF device see-through glasses). This method ensures the creation of detailed, high-quality datasets for 3D models, with potential applications in Building Information Modeling (BIM) but not limited.

Ali Lenjani, Shirley J. Dyke, Ilias Bilionis et al.

In post-event reconnaissance missions, engineers and researchers collect perishable information about damaged buildings in the affected geographical region to learn from the consequences of the event. A typical post-event reconnaissance mission is conducted by first doing a preliminary survey, followed by a detailed survey. The preliminary survey is typically conducted by driving slowly along a pre-determined route, observing the damage, and noting where further detailed data should be collected. This involves several manual, time-consuming steps that can be accelerated by exploiting recent advances in computer vision and artificial intelligence. The objective of this work is to develop and validate an automated technique to support post-event reconnaissance teams in the rapid collection of reliable and sufficiently comprehensive data, for planning the detailed survey. The technique incorporates several methods designed to automate the process of categorizing buildings based on their key physical attributes, and rapidly assessing their post-event structural condition. It is divided into pre-event and post-event streams, each intending to first extract all possible information about the target buildings using both pre-event and post-event images. Algorithms based on convolutional neural network (CNNs) are implemented for scene (image) classification. A probabilistic approach is developed to fuse the results obtained from analyzing several images to yield a robust decision regarding the attributes and condition of a target building. We validate the technique using post-event images captured during reconnaissance missions that took place after hurricanes Harvey and Irma. The validation data were collected by a structural wind and coastal engineering reconnaissance team, the National Science Foundation (NSF) funded Structural Extreme Events Reconnaissance (StEER) Network.

Ali Lenjani, Chul Min Yeum, Shirley Dyke et al.

After a disaster, teams of structural engineers collect vast amounts of images from damaged buildings to obtain new knowledge and extract lessons from the event. However, in many cases, the images collected are captured without sufficient spatial context. When damage is severe, it may be quite difficult to even recognize the building. Accessing images of the pre-disaster condition of those buildings is required to accurately identify the cause of the failure or the actual loss in the building. Here, to address this issue, we develop a method to automatically extract pre-event building images from 360o panorama images (panoramas). By providing a geotagged image collected near the target building as the input, panoramas close to the input image location are automatically downloaded through street view services (e.g., Google or Bing in the United States). By computing the geometric relationship between the panoramas and the target building, the most suitable projection direction for each panorama is identified to generate high-quality 2D images of the building. Region-based convolutional neural networks are exploited to recognize the building within those 2D images. Several panoramas are used so that the detected building images provide various viewpoints of the building. To demonstrate the capability of the technique, we consider residential buildings in Holiday Beach, Texas, the United States which experienced significant devastation in Hurricane Harvey in 2017. Using geotagged images gathered during actual post-disaster building reconnaissance missions, we verify the method by successfully extracting residential building images from Google Street View images, which were captured before the event.

Chul Min Yeum, Ali Lenjani, Shirley J. Dyke et al.

After a disaster, teams of structural engineers collect vast amounts of images from damaged buildings to obtain lessons and gain knowledge from the event. Images of damaged buildings and components provide valuable evidence to understand the consequences on our structures. However, in many cases, images of damaged buildings are often captured without sufficient spatial context. Also, they may be hard to recognize in cases with severe damage. Incorporating past images showing a pre-disaster condition of such buildings is helpful to accurately evaluate possible circumstances related to a building's failure. One of the best resources to observe the pre-disaster condition of the buildings is Google Street View. A sequence of 360 panorama images which are captured along streets enables all-around views at each location on the street. Once a user knows the GPS information near the building, all external views of the building can be made available. In this study, we develop an automated technique to extract past building images from 360 panorama images serviced by Google Street View. Users only need to provide a geo-tagged image, collected near the target building, and the rest of the process is fully automated. High-quality and undistorted building images are extracted from past panoramas. Since the panoramas are collected from various locations near the building along the street, the user can identify its pre-disaster conditions from the full set of external views.