Abstract:We propose a method to generate highly detailed, textured 3D models of large environments from RGB-D sequences. Our system runs in real-time on a standard desktop PC with a state-of-the-art graphics card. To reduce the memory consumption, we fuse the acquired depth maps and colors in a multi-scale octree representation of a signed distance function. To estimate the camera poses, we construct a pose graph and use dense image alignment to determine the relative pose between pairs of frames. We add edges between … Show more
“…The generation of the TSDFs f i : Ω 3 ⊂ R 3 → R follows related work [11,21,22,25]: given the i-th frame of range data D i : Ω 2 → R + together with the corresponding projection π i : R 3 → Ω 2 , the idea is to compute the signed distance φ i between the surface and each point x ∈ Ω 3 of the reconstruction volume along the line of sight. Furthermore, scaling with δ and truncation to [−1, +1] is performed to retrieve the final TSDF f i…”
Section: Tsdf-octree Generationmentioning
confidence: 99%
“…Octrees are established in many fields and are often used to alleviate computational burdens. Recent work ( [7,22,27]) uses Octrees for range data integration to map the environment, but employs simple update rules to encompass newly seen data without any optimization whatsoever. For simulation problems these partitioning structures are usually of static auxiliary nature (e.g.…”
Section: Arxiv:160807411v1 [Cscv] 26 Aug 2016mentioning
confidence: 99%
“…In [15,16], the authors deal with spatially adaptive techniques for incompressible flow and state their surprise about the high accuracy of Octree-based mesh refinement even for smallscale structures. The works [7,22,27] use dynamic Octree-based representations to store scene geometry but do no conduct any elaborate schemes for the integration since their main interest is mapping and efficient storage/updates for large-scale problems. [9] introduces a data structure that includes a hierarchical partitioning where each cube uses a runlength encoding.…”
Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime. Especially for sparse geometric structures, volumetric representations produce a huge computational overhead. We present an efficient way to fuse range data via a variational Octree-based minimization approach by taking the actual range data geometry into account. We transform the data into Octree-based truncated signed distance fields and show how the optimization can be conducted on the newly created structures. The main challenge is to uphold speed and a low memory footprint without sacrificing the solutions' accuracy during optimization. We explain how to dynamically adjust the optimizer's geometric structure via joining/splitting of Octree nodes and how to define the operators. We evaluate on various datasets and outline the suitability in terms of performance and geometric accuracy.
“…The generation of the TSDFs f i : Ω 3 ⊂ R 3 → R follows related work [11,21,22,25]: given the i-th frame of range data D i : Ω 2 → R + together with the corresponding projection π i : R 3 → Ω 2 , the idea is to compute the signed distance φ i between the surface and each point x ∈ Ω 3 of the reconstruction volume along the line of sight. Furthermore, scaling with δ and truncation to [−1, +1] is performed to retrieve the final TSDF f i…”
Section: Tsdf-octree Generationmentioning
confidence: 99%
“…Octrees are established in many fields and are often used to alleviate computational burdens. Recent work ( [7,22,27]) uses Octrees for range data integration to map the environment, but employs simple update rules to encompass newly seen data without any optimization whatsoever. For simulation problems these partitioning structures are usually of static auxiliary nature (e.g.…”
Section: Arxiv:160807411v1 [Cscv] 26 Aug 2016mentioning
confidence: 99%
“…In [15,16], the authors deal with spatially adaptive techniques for incompressible flow and state their surprise about the high accuracy of Octree-based mesh refinement even for smallscale structures. The works [7,22,27] use dynamic Octree-based representations to store scene geometry but do no conduct any elaborate schemes for the integration since their main interest is mapping and efficient storage/updates for large-scale problems. [9] introduces a data structure that includes a hierarchical partitioning where each cube uses a runlength encoding.…”
Volume-based reconstruction is usually expensive both in terms of memory consumption and runtime. Especially for sparse geometric structures, volumetric representations produce a huge computational overhead. We present an efficient way to fuse range data via a variational Octree-based minimization approach by taking the actual range data geometry into account. We transform the data into Octree-based truncated signed distance fields and show how the optimization can be conducted on the newly created structures. The main challenge is to uphold speed and a low memory footprint without sacrificing the solutions' accuracy during optimization. We explain how to dynamically adjust the optimizer's geometric structure via joining/splitting of Octree nodes and how to define the operators. We evaluate on various datasets and outline the suitability in terms of performance and geometric accuracy.
“…Common representations for 3D models include point clouds, surfels [10], triangle meshes [27], and signed distance functions [6]. Octrees allow for efficient data storage and fusion at multiple scales [9,24,28]. While KinectFusion [17] demonstrated that impressive 3D models can be acquired by tracking and fusing the depth images directly into a signed distance volume, drift will accumulate in the 3D model and inevitably lead to inconsistencies.…”
Abstract. The key contribution of this paper is a novel submapping technique for RGB-D-based bundle adjustment. Our approach significantly speeds up 3D object reconstruction with respect to full bundle adjustment while generating visually compelling 3D models of high metric accuracy. While submapping has been explored previously for mono and stereo cameras, we are the first to transfer and adapt this concept to RGB-D sensors and to provide a detailed analysis of the resulting gain. In our approach, we partition the input data uniformly into submaps to optimize them individually by minimizing the 3D alignment error. Subsequently, we fix the interior variables and optimize only over the separator variables between the submaps. As we demonstrate in this paper, our method reduces the runtime of full bundle adjustment by 32% on average while still being able to deal with real-world noise of cheap commodity sensors. We evaluated our method on a large number of benchmark datasets, and found that we outperform several state-ofthe-art approaches both in terms of speed and accuracy. Furthermore, we present highly accurate 3D reconstructions of various objects to demonstrate the validity of our approach.
“…In order to overcome the size limit of the volumetric grid, moving volume approaches are adopted in [Roth and Vona 2012;Whelan et al 2012] to swap out voxels not in view of the depth camera from the graphics memory. In [Steinbrucker et al 2013], a multi-scale octree data structure and dense image alignment are adopted to reconstruct large-scale indoor scenes such as nine rooms along a corridor. Hierarchical spatial data structures and streaming algorithms are developed in [Chen et al 2013] to extend KinectFusion to large-scale scenes.…”
Figure 1: A lab scene (100m 2 ) reconstructed on-the-fly. The complete scan finished within 70 minutes. Top left: the final reconstructed model by our system, which contains planar regions (polygons) and extracted meshes for separate objects, created and refined progressively in real-time by our online analysis procedure during the scan. Top right: the result of the plane/object labeling procedure, which provides the segmentation of planes and objects for the online analysis. The colors distinguish planar regions and objects by their labels in the volumetric data structure. Bottom: close-up views of the reconstructed scene.
AbstractWe propose a real-time approach for indoor scene reconstruction. It is capable of producing a ready-to-use 3D geometric model even while the user is still scanning the environment with a consumer depth camera. Our approach features explicit representations of planar regions and non-planar objects extracted from the noisy feed of the depth camera, via an online structure analysis on the dynamic, incomplete data. The structural information is incorporated into the volumetric representation of the scene, resulting in a seamless integration with KinectFusion's global data structure and an efficient implementation of the whole reconstruction process. Moreover, heuristics based on rectilinear shapes in typical indoor scenes effectively eliminate camera tracking drift and further improve reconstruction accuracy. The instantaneous feedback enabled by our on-the-fly structure analysis, including repeated object recognition, allows the user to selectively scan the scene and produce high fidelity large-scale models efficiently. We demonstrate the capability of our system with real-life examples. *
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.