Colored Point Cloud Registration Revisited

By Jaesik Park, Qian-Yi Zhou, Vladlen Koltun. IEEE International Conference on Computer Vision, 2017

390 citations recorded by the source corpus.

Subfields: Aerospace Engineering, Environmental Engineering, Geology

View Paper: https://www.semanticscholar.org/paper/2a59411d40995fdfcd88b5c0ddd59161ac6eccad

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Aerospace Engineering

In Environmental Engineering

In Geology

Citations in the corpus

LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World (2020, methodology): “To further refine the shape and account for errors in point cloud alignment for moving objects, we apply an iterative colorICP algorithm, where we use recorded intensity as the color feature [27].”
Image Matching from Handcrafted to Deep Features: A Survey (2020, background): “Danelljan et al. (2016) and Park et al. (2017) considered the color information of point sets, whereas Evangelidis and Horaud (2018) and Giraldo et al. (2017) addressed the problem of joint registration of multiple point sets.”
Open3D: A Modern Library for 3D Data Processing (2018, methodology): “We have veriﬁed that the functionality of Open3D is sufﬁcient by using it to implement complete workﬂows such as large-scale scene reconstruction [5, 15].”
Deep Depth Completion of a Single RGB-D Image (2018, background): “This approach is costly and time-consuming – the largest public datasets of this type cover a handful of indoor scenes (e.g., [57, 62, 75]).”
ConceptFusion: Open-set Multimodal 3D Mapping (2023, methodology): “Frame preprocessing: Each incoming frame It (comprising a color image Ct and a depth image Dt) is preprocessed to compute vertex-normal maps (Vt, Nt) and camera pose estimates Pt [30, 54].”
BAD SLAM: Bundle Adjusted Direct RGB-D SLAM (2019, neutral): “Fragment-based optimization fuses together chunks of frames into fragments and then optimizes the global (rigid) fragment alignment [6,15,27,49].”
A Survey on 3D Gaussian Splatting (2024, neutral): “These approaches adopt a hybrid deformation strategy: linear blend skinning handles rigid skeletal transformations such as joint rotations, while pose-conditioned deformation fields account for secondary non-rigid effects like muscle jiggles.”
Deep Global Registration (2020, methodology): “We test the modiﬁed pipeline on the Augmented ICL-NUIM dataset [6, 18] for quantitative trajectory results, and Indoor LiDAR RGB-D dataset [32] and Stanford RGB-D dataset [6] for qualitative registration visualizations.”