Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding
This work addresses a limitation in planar reconstruction for real-time applications like visual SLAM and human-robot interaction, though it is incremental as it builds on existing associative embedding techniques.
The paper tackles the problem of single-image piece-wise planar 3D reconstruction, which involves segmenting plane instances and recovering 3D parameters, by proposing a two-stage method based on associative embedding that detects an arbitrary number of planes and runs at 30 fps, achieving competitive results on public datasets.
Single-image piece-wise planar 3D reconstruction aims to simultaneously segment plane instances and recover 3D plane parameters from an image. Most recent approaches leverage convolutional neural networks (CNNs) and achieve promising results. However, these methods are limited to detecting a fixed number of planes with certain learned order. To tackle this problem, we propose a novel two-stage method based on associative embedding, inspired by its recent success in instance segmentation. In the first stage, we train a CNN to map each pixel to an embedding space where pixels from the same plane instance have similar embeddings. Then, the plane instances are obtained by grouping the embedding vectors in planar regions via an efficient mean shift clustering algorithm. In the second stage, we estimate the parameter for each plane instance by considering both pixel-level and instance-level consistencies. With the proposed method, we are able to detect an arbitrary number of planes. Extensive experiments on public datasets validate the effectiveness and efficiency of our method. Furthermore, our method runs at 30 fps at the testing time, thus could facilitate many real-time applications such as visual SLAM and human-robot interaction. Code is available at https://github.com/svip-lab/PlanarReconstruction.