PU-EVA: An Edge-Vector based Approximation Solution for Flexible-scale Point Cloud Upsampling

Abstract

High-quality point clouds have practical significance for point-based rendering, semantic understanding, and surface reconstruction. Upsampling sparse, noisy and nonuniform 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 flexible 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 the neighboring connectivity via affine combinations based on edge vectors, and restricts the approximation error within the second-order term of Taylor's Expansion. The EVA upsampling decouples the upsampling scales with network architecture, achieving the flexible 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.

PU-MFA: Point Cloud Up-Sampling via Multi-Scale Features Attention

“…Pugeo-Net [ 19 ] showed good performance at generating high-quality dense point set by using it in Feature Recalibration. PU-EVA [ 6 ] showed successfully generating up-sampled point set using an EVA Expansion Unit with the mechanism. Dis-PU [ 13 ] performed well using the Local Refinement Unit with self-attention applied to the generated point set.…”

“…This study evaluated the method using CD, HD, and P2F metrics, as in prior studies [ 5 , 6 , 13 ]. CD is a metric that measures the similarity between a set of GT points and a set of predicted points for each point, and HD is an evaluation metric that measures the outliers in a set of predicted points based on a set of GT points.…”

“…The proposed method was compared with three state-of-the-art methods: Dis-pu [ 13 ], PU-EVA [ 6 ], and PU-Transformer [ 5 ] to validate the method. For an exact comparison, all methods were implemented using pytorch [ 29 ] version 1.7.0 on Ubuntu 20.04 and trained on the same Intel i9-10980XE CPU and NVIDIA TITAN RTX environment.…”

“…Similar to learning-based image super-resolution studies [ 3 , 4 ], various learning-based point cloud up-sampling studies [ 5 , 6 , 7 ] show better performance of generating high-quality dense point set than traditional point cloud up-sampling studies [ 8 , 9 ]. Intuitively, the image super-resolution tasks and the point cloud up-sampling tasks are similar.…”

“…These studies have reported that they are excellent for generating dense point sets, but the last feature extracted by the feature extractor has a limitation in that the details of the sparse point set are diluted features because the output of each layer is used as the input of the next layer. Dis-PU [ 13 ], PU-EVA [ 6 ], and PU-Transformer [ 5 ] showed successful performance of generating high-quality dense point set using the self-attention mechanism to learn long-range dependencies between points. However, there is a limit to applying the attention mechanism with limited information because the key, query, and value of the self-attention mechanism are generated from the same input.…”