GeoFormer: Learning Point Cloud Completion with Tri-Plane Integrated Transformer
Open Access
- 28 October 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 8952-8961
Abstract
Point cloud completion aims to recover accurate global geometry and preserve fine-grained local details from partial point clouds. Conventional methods typically predict unseen points directly from 3D point cloud coordinates or use self-projected multi-view depth maps to ease this task. However, these gray-scale depth maps cannot reach multi-view consistency, consequently restricting the performance. In this paper, we introduce a GeoFormer that simultaneously enhances the global geometric structure of the points and improves the local details. Specifically, we design a CCM Feature Enhanced Point Generator to integrate image features from multi-view consistent canonical coordinate maps (CCMs) and align them with pure point features, thereby enhancing the global geometry feature. Additionally, we employ the Multi-scale Geometry-aware Upsampler module to progressively enhance local details. This is achieved through cross attention between the multi-scale features extracted from the partial input and the features derived from previously estimated points. Extensive experiments on the PCN, ShapeNet-55/34, and KITTI benchmarks demonstrate that our GeoFormer outperforms recent methods, achieving the state-of-the-art performance. Our code is available at https://github.com/Jinpeng-Yu/GeoFormer.Keywords
All Related Versions
Funding Information
- National Natural Science Foundation of China (62172279,61932020)
This publication has 41 references indexed in Scilit:
- SeedFormer: Patch Seeds Based Point Cloud Completion with Upsample Transformer2022
- FBNet: Feedback Network for Point Cloud Completion2022
- GeneCGAN: A conditional generative adversarial network based on genetic tree for point cloud reconstructionNeurocomputing, 2021
- Towards point cloud completion: Point Rank Sampling and Cross-Cascade Graph CNNNeurocomputing, 2021
- GRNet: Gridding Residual Network for Dense Point Cloud Completion2020
- Deep Continuous Fusion for Multi-sensor 3D Object Detection2018
- PCN: Point Completion Network2018
- FoldingNet: Point Cloud Auto-Encoder via Deep Grid Deformation2018
- Shape Completion Using 3D-Encoder-Predictor CNNs and Shape Synthesis2017
- Deep Residual Learning for Image Recognition2016