PU-EVA: An Edge-Vector Based Approximation Solution for Flexible-Scale Point Cloud Upsampling

Luqing Luo, Lulu Tang, Wanyi Zhou, Shizheng Wang, Zhi-Xin Yang; Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 16208-16217

Abstract


High-quality point clouds have practical significance for point-based rendering, semantic understanding, and surface reconstruction. Upsampling sparse, noisy and non-uniform point clouds for a denser and more regular approximation of target objects is a desirable but challenging task. Most existing methods duplicate point features for upsampling, constraining the upsampling scales at a fixed rate. In this work, the arbitrary point clouds upsampling rates are achieved via edge-vector based affine combinations, and a novel design of Edge-Vector based Approximation for Flexible-scale Point clouds Upsampling (PU-EVA) is proposed. The edge-vector based approximation encodes neighboring connectivity via affine combinations based on edge vectors, and restricts the approximation error within a second-order term of Taylor's Expansion. Moreover, the EVA upsampling decouples the upsampling scales with network architecture, achieving the arbitrary upsampling rates in one-time training. Qualitative and quantitative evaluations demonstrate that the proposed PU-EVA outperforms the state-of-the-arts in terms of proximity-to-surface, distribution uniformity, and geometric details preservation.

Related Material


[pdf] [supp] [arXiv]
[bibtex]
@InProceedings{Luo_2021_ICCV, author = {Luo, Luqing and Tang, Lulu and Zhou, Wanyi and Wang, Shizheng and Yang, Zhi-Xin}, title = {PU-EVA: An Edge-Vector Based Approximation Solution for Flexible-Scale Point Cloud Upsampling}, booktitle = {Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)}, month = {October}, year = {2021}, pages = {16208-16217} }