-
[pdf]
[supp]
[arXiv]
[bibtex]@InProceedings{Shi_2023_ICCV, author = {Shi, Jingjia and Zhi, Shuaifeng and Xu, Kai}, title = {PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2023}, pages = {9377-9386} }
PlaneRecTR: Unified Query Learning for 3D Plane Recovery from a Single View
Abstract
3D plane recovery from a single image can usually be divided into several subtasks of plane detection, segmentation, parameter estimation and possibly depth estimation. Previous works tend to solve it by either extending the RCNN-based segmentation network or the dense pixel embedding-based clustering framework. However, none of them tried to integrate above related subtasks into a unified framework but treated them separately and sequentially, which we suspect is potentially a main source of performance limitation for existing approaches. Motivated by this finding and the success of query-based learning in enriching reasoning among semantic entities, in this paper, we propose PlaneRecTR, a Transformer-based architecture, which for the first time unifies all subtasks related to single-view plane recovery with a single compact model. Extensive quantitative and qualitative experiments demonstrate that our proposed unified learning achieves mutual benefits across subtasks, obtaining a new state-of-the-art performance on public ScanNet and NYUv2-Plane datasets.
Related Material