Planecell: Representing the 3D Space with Planes
This work improves 3D reconstruction for applications like robotics or autonomous driving, but it appears incremental as it builds on existing representation methods.
The paper tackled the problem of 3D reconstruction from stereo cameras by addressing challenges in pixel aggregation and information retention, proposing a planecell representation that extracts and merges depth planes, and demonstrated superior accuracy, memory efficiency, and applicability compared to other methods on KITTI and Middlebury datasets.
Reconstruction based on the stereo camera has received considerable attention recently, but two particular challenges still remain. The first concerns the need to aggregate similar pixels in an effective approach, and the second is to maintain as much of the available information as possible while ensuring sufficient accuracy. To overcome these issues, we propose a new 3D representation method, namely, planecell, that extracts planarity from the depth-assisted image segmentation and then projects these depth planes into the 3D world. An energy function formulated from Conditional Random Field that generalizes the planar relationships is maximized to merge coplanar segments. We evaluate our method with a variety of reconstruction baselines on both KITTI and Middlebury datasets, and the results indicate the superiorities compared to other 3D space representation methods in accuracy, memory requirements and further applications.