Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction

Maier, Robert; Schaller, Raphael; Cremers, Daniel

doi:10.5244/c.31.158

Cited by 14 publications

(25 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This approach produces state-of-the-art results in terms of reconstruction quality, but requires significant computational resources. Several recent works [18], [19] have proposed efficiency improvements to the original scheme, principally by utilizing keyframes and computing the global reconstruction as a function of these keyframes only, as well as speed-ups to the original global optimization scheme. In contrast to our proposal however, these works suggest to maintain a single monolithic map.…”

Section: Related Workmentioning

confidence: 99%

Voxgraph: Globally Consistent, Volumetric Mapping Using Signed Distance Function Submaps

Reijgwart

Millane

Oleynikova

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Globally consistent dense maps are a key requirement for long-term robot navigation in complex environments. While previous works have addressed the challenges of dense mapping and global consistency, most require more computational resources than may be available on-board small robots. We propose a framework that creates globally consistent volumetric maps on a CPU and is lightweight enough to run on computationally constrained platforms. Our approach represents the environment as a collection of overlapping Signed Distance Function (SDF) submaps, and maintains global consistency by computing an optimal alignment of the submap collection. By exploiting the underlying SDF representation, we generate correspondencefree constraints between submap pairs that are computationally efficient enough to optimize the global problem each time a new submap is added. We deploy the proposed system on a hexacopter Micro Aerial Vehicle (MAV) with an Intel i7-8650U CPU in two realistic scenarios: mapping a large-scale area using a 3D LiDAR, and mapping an industrial space using an RGB-D camera. In the large-scale outdoor experiments, the system optimizes a 120x80 m map in less than 4 s and produces absolute trajectory RMSEs of less than 1 m over 400 m trajectories. Our complete system, called voxgraph, is available as open source 1 .

show abstract

Section: Related Workmentioning

confidence: 99%

Voxgraph: Globally Consistent, Volumetric Mapping Using Signed Distance Function Submaps

Reijgwart

Millane

Oleynikova

et al. 2020

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

show abstract

“…Furthermore, the replacement of the TSDF representation by a highresolution binary voxel grid has also been considered by Reichl et al [25] to improve the scalability and reduce the memory requirements. Recent extensions include the detection of loop closures [2,11,16] to reduce drift artifacts in camera localization as well as multi-client collaborative acquisition and reconstruction of static scenes [6]. This progress in real-time capturing enabled the development of various telepresence applications.…”

Section: Related Workmentioning

confidence: 99%

“…tracking [9,12,21,23,25,29,31] (as also used in the SLAMCast system) or using bundle adjustment for globally-consistent reconstruction [2,11]. Using this pose, non-visible voxel block data are streamed out to CPU memory whereas visible blocks in CPU memory are streamed back into GPU memory [12,16,23,25]. In the next step, new voxel blocks are allocated in the volume and the RGB-D data are fused into the volumetric model.…”

Section: Cpu -Gpu Streaming Data Fusion Model Visualizationmentioning

confidence: 99%

“…(a) heating room: B,16.5ms(8.6ms), 3482MB (b) heating room: B+DDF, 10.3ms (4.4ms), 1815MB (c) heating room: B+VBAD, 13.2ms (6.6ms), 2548MB (d) heating room: B+MCVBP, 16.1ms (8.7ms), 3482MB (e) heating room: Ours, 9.7ms (3.3ms), 1442MB (f) lounge: B, 10.9ms (5.0ms), 1286MB (g) lounge: B+DDF, 10.0ms (4.4ms), 1106MB (h) lounge: B+VBAD, 10.0ms (5.4ms), 1081MB (i) lounge: B+MCVBP, 10.9ms (5.2ms), 1286MB (j) lounge: Ours, 9.7ms (4.3ms), 983MB Comparison of visual quality, mean runtime (and standard deviation) as well as memory requirements for each system variant. All individual contributions reduced the amount of reconstruction artifacts while improving the overall reconstruction performance.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Efficient 3D Reconstruction and Streaming for Group-Scale Multi-Client Live Telepresence

Stotko

Krumpen

Weinmann

et al. 2019

2019 IEEE International Symposium on Mixed and Augmented Reality (ISMAR)

View full text Add to dashboard Cite

SLAMCast 4 ECs Ours 24 ECsFigure 1: Illustration of our novel highly scalable multi-client live telepresence system. While previous approaches are limited to a low number of up to 4 remote exploration clients, our system is capable of providing an immersive telepresence experience within a live-captured high-quality scene reconstruction to more than 24 clients simultaneously without introducing further latency. ABSTRACTSharing live telepresence experiences for teleconferencing or remote collaboration receives increasing interest with the recent progress in capturing and AR/VR technology. Whereas impressive telepresence systems have been proposed on top of on-the-fly scene capture, data transmission and visualization, these systems are restricted to the immersion of single or up to a low number of users into the respective scenarios. In this paper, we direct our attention on immersing significantly larger groups of people into live-captured scenes as required in education, entertainment or collaboration scenarios. For this purpose, rather than abandoning previous approaches, we present a range of optimizations of the involved reconstruction and streaming components that allow the immersion of a group of more than 24 users within the same scene -which is about a factor of 6 higher than in previous work -without introducing further latency or changing the involved consumer hardware setup. We demonstrate that our optimized system is capable of generating high-quality scene reconstructions as well as providing an immersive viewing experience to a large group of people within these live-captured scenes.

show abstract

“…Some high-precision sensor-tracking methods [26,31,32] using the features of volumetric representation are also proposed. Furthermore, some other research has focused on introducing global adjustment in real-time reconstruction to reduce the tracking drift accumulation caused by frame-to-frame registration, as well as the corresponding voxel data fast update strategy [19,[33][34][35][36]. In addition to the static scene reconstruction, voxel-based methods can also be used in the 3D reconstruction of some dynamic scenes, such as reconstructing the human body surface undergoing free non-rigid motion [25,[37][38][39][40][41].…”

Section: Introductionmentioning

confidence: 99%

Real-Time 3D Reconstruction of Thin Surface Based on Laser Line Scanner

Zheng

Zhu

et al. 2020

Sensors

View full text Add to dashboard Cite

The truncated signed distance field (TSDF) has been applied as a fast, accurate, and flexible geometric fusion method in 3D reconstruction of industrial products based on a hand-held laser line scanner. However, this method has some problems for the surface reconstruction of thin products. The surface mesh will collapse to the interior of the model, resulting in some topological errors, such as overlap, intersections, or gaps. Meanwhile, the existing TSDF method ensures real-time performance through significant graphics processing unit (GPU) memory usage, which limits the scale of reconstruction scene. In this work, we propose three improvements to the existing TSDF methods, including: (i) a thin surface attribution judgment method in real-time processing that solves the problem of interference between the opposite sides of the thin surface; we distinguish measurements originating from different parts of a thin surface by the angle between the surface normal and the observation line of sight; (ii) a post-processing method to automatically detect and repair the topological errors in some areas where misjudgment of thin-surface attribution may occur; (iii) a framework that integrates the central processing unit (CPU) and GPU resources to implement our 3D reconstruction approach, which ensures real-time performance and reduces GPU memory usage. The proposed results show that this method can provide more accurate 3D reconstruction of a thin surface, which is similar to the state-of-the-art laser line scanners with 0.02 mm accuracy. In terms of performance, the algorithm can guarantee a frame rate of more than 60 frames per second (FPS) with the GPU memory footprint under 500 MB. In total, the proposed method can achieve a real-time and high-precision 3D reconstruction of a thin surface.

show abstract

Efficient Online Surface Correction for Real-time Large-Scale 3D Reconstruction

Cited by 14 publications

References 20 publications

Voxgraph: Globally Consistent, Volumetric Mapping Using Signed Distance Function Submaps

Voxgraph: Globally Consistent, Volumetric Mapping Using Signed Distance Function Submaps

Efficient 3D Reconstruction and Streaming for Group-Scale Multi-Client Live Telepresence

Real-Time 3D Reconstruction of Thin Surface Based on Laser Line Scanner

Contact Info

Product

Resources

About