GRNet: Gridding Residual Network for Dense Point Cloud Completion

By Haozhe Xie, Hongxun Yao, Shangchen Zhou, Jiageng Mao, Shengping Zhang, Wenxiu Sun. European Conference on Computer Vision, 2020

449 citations recorded by the source corpus.

Estimating the complete 3D point cloud from an incomplete one is a key problem in many vision and robotics applications. Mainstream methods (e.g., PCN and TopNet) use Multi-layer Perceptrons (MLPs) to directly process point clouds, which may cause the loss of details because the structural and context of point clouds are not fully considered. To solve this problem, we introduce 3D grids as intermediate representations to regularize unordered point clouds. We therefore propose a novel Gridding Residual Network (GRNet) for point cloud completion. In particular, we devise two novel differentiable layers, named Gridding and Gridding Reverse, to convert between point clouds and 3D grids without losing structural information. We also present the differentiable Cubic Feature Sampling layer to extract features of neighboring points, which preserves context information. In addition, we design a new loss function, namely Gridding Loss, to calculate the L1 distance between the 3D grids of the predicted and ground truth point clouds, which is helpful to recover details. Experimental results indicate that the proposed GRNet performs favorably against state-of-the-art methods on the ShapeNet, Completion3D, and KITTI benchmarks.

Subfields: Computational Mechanics, Computer Graphics and Computer-Aided Design, Geology

View Paper: https://www.semanticscholar.org/paper/477a1de90ba8f22e4f4068ff8d6233afe74db936

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Bo Dai
2. Chen Change Loy
3. Peng Xiang
4. Xin Wen
5. Wen Zheng
6. Yan-Pei Cao
7. Zhizhong Han
8. Pengfei Wan

In Computer Graphics and Computer-Aided Design

1. Bo Dai
2. Chen Change Loy

In Geology

1. Bo Dai
2. Chen Change Loy
3. Zhizhong Han
4. Yu-Shen Liu

Citations in the corpus

• SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution with Skip-Transformer (2021, methodology): “Despite of this, our SnowflakeNet still achieves the superior performance over folding-based methods including SA-Net [53] and FoldingNet [56], and we are also the best among the coarse-to-fine methods including TopNet [43] and GRNet [55].”
• Unsupervised 3D Shape Completion through GAN Inversion (2021, background): “Owing to the coarse-to-fine strategy [28, 21, 15, 30, 34], they achieve impressive results on in-domain data, but may fail to sufficiently generalize to real-world scans or partial shapes in other forms.”