Removing outlier correspondences is one of the critical steps for successful feature-based point cloud registration.
Semantic segmentation and semantic edge detection can be seen as two dual problems with close relationships in computer vision.
Ranked #10 on Semantic Segmentation on S3DIS
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds.
Ranked #4 on Point Cloud Registration on 3DMatch Benchmark
In this paper, we leverage a 3D fully convolutional network for 3D point clouds, and propose a novel and practical learning mechanism that densely predicts both a detection score and a description feature for each 3D point.
Ranked #2 on Point Cloud Registration on KITTI
In this paper, we study the problem of multi-view sketch correspondence, where we take as input multiple freehand sketches with different views of the same object and predict as output the semantic correspondence among the sketches.
To bridge the gap between these two spaces in neural networks, we propose a neural line rasterization module to convert the vector sketch along with the attention estimated by RNN into a bitmap image, which is subsequently consumed by CNN.
In this paper, we propose a structural segmentation algorithm to partition multi-view stereo reconstructed surfaces of large-scale urban environments into structural segments.