Joint Layout Estimation and Global Multi-View Registration for Indoor Reconstruction

Lee, Jeong-Kyun; Yea, Jaewon; Park, Min-Gyu; Yoon, Kuk-Jin

doi:10.48550/arxiv.1704.07632

Cited by 1 publication

(3 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most commmon approach is to detect planes in RGB-D scans, establish correspondences between matching features, and solve for the camera poses that align the corresponding features [29,30,31,32,33,34,35,36]. More recent approaches build models comprising planar patches, possibly with geometric constraints [4,37], and match planar features found in scans to planar patches in the models [4,5,6,7,8]. The search for correspondences is often aided by hand-tuned descriptors designed to detect overlapping surface regions.…”

Section: Related Workmentioning

confidence: 99%

“…We solve for the aligning transformation by taking partial derivatives of Equation (5) with respect to the transformation parameters in r and t. This results in a linear system Cx = b where x = [r T , t T ] and b is the residual vector. C is a 6 × 6 "covariance matrix" of the rotational and translational components, accumulated from the sample points:…”

Section: Stability Analysismentioning

confidence: 99%

“…An alternative is to detect planar features and associate them across frames with coplanarity, parallelism, and perpendicularity constraints [3,4,5,6,7,8,9]. Recent work has shown compelling evidence that planar patches can be detected Fig.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

PlaneMatch: Patch Coplanarity Prediction for Robust RGB-D Reconstruction

Shi

Nießner

et al. 2018

Computer Vision – ECCV 2018

View full text Add to dashboard Cite

We introduce a novel RGB-D patch descriptor designed for detecting coplanar surfaces in SLAM reconstruction. The core of our method is a deep convolutional neural network that takes in RGB, depth, and normal information of a planar patch in an image and outputs a descriptor that can be used to find coplanar patches from other images. We train the network on 10 million triplets of coplanar and non-coplanar patches, and evaluate on a new coplanarity benchmark created from commodity RGB-D scans. Experiments show that our learned descriptor outperforms alternatives extended for this new task by a significant margin. In addition, we demonstrate the benefits of coplanarity matching in a robust RGBD reconstruction formulation. We find that coplanarity constraints detected with our method are sufficient to get reconstruction results comparable to state-of-the-art frameworks on most scenes, but outperform other methods on established benchmarks when combined with traditional keypoint matching.

show abstract