FPConv: Learning Local Flattening for Point Convolution

Lin, Yiran; Yan, Zizheng; Huang, Haibin; Du, Dong; Liu, Ligang; Cui, Shuguang; Han, Xiaoguang

doi:10.1109/cvpr42600.2020.00435

Cited by 135 publications

(100 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There are also some other works [16], [28], [36], [42]- [46] that perform CNN-like operations by establishing kNN graphs in local regions. FPConv [47] adopts a local flattening by a weight map to project the neighboring points onto a 2D grid and thus apply 2D convolution for feature extraction. The previous local aggregation operators are revisited in [48], and a simple local aggregation operator without learnable weights named Position Pooling (PosPool) is proposed.…”

Section: Point-based Methodsmentioning

confidence: 99%

A Lightweight Structure Based on Feature Fusion for Point Cloud Analysis

Zheng

Sun

2021

IEEE Access

View full text Add to dashboard Cite

Point cloud analysis is challenging due to the irregularity and sparsity, making it difficult to capture the underlying geometric characteristics. This paper proposes a lightweight structure that effectively aggregates the local patterns and the spatial layout of them extracted from the irregular and sparse point cloud. Unlike previous works that seek sophisticated feature extraction methods, the key to this structure is simultaneously exploring the local features and their distribution features in a concise manner. Specifically, the two features, which correspond to two different scales, are extracted independently and then fused. In this way, an abstract shape-level feature that contains much shape awareness and robustness is obtained. Moreover, since the structure exhibits rapid convergence with conventional learning schedule, we upgrade it by introducing the snapshot ensemble and creatively design a more flexible and effective cyclic annealing learning schedule. We evaluate the structure on challenging benchmarks, and experiment results prove that our model achieves on-par or better performance than previous state-of-the-art (SOTA) methods, although with the simple shared multi-layer perceptrons (MLPs) as feature extractors.

show abstract

Section: Point-based Methodsmentioning

confidence: 99%

A Lightweight Structure Based on Feature Fusion for Point Cloud Analysis

Zheng

Sun

2021

IEEE Access

View full text Add to dashboard Cite

show abstract

“…FPConv [45] is a 2D convolution algorithm that can directly process the surface geometry of a point cloud without converting it to an intermediate representation (e.g., a 3D grid or graph). FPConv is able to apply regular 2D convolution to effective feature learning by automatically learning weight maps to gently project surrounding points onto a 2D grid for local expansion.…”

Section: Deep Learning Algorithms For Point Clouds Data 221 Deep Learning Algorithmsmentioning

confidence: 99%

Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Dong

Chen

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Automatic acquisition of the canopy volume parameters of the Citrus reticulate Blanco cv. Shatangju tree is of great significance to precision management of the orchard. This research combined the point cloud deep learning algorithm with the volume calculation algorithm to segment the canopy of the Citrus reticulate Blanco cv. Shatangju trees. The 3D (Three-Dimensional) point cloud model of a Citrus reticulate Blanco cv. Shatangju orchard was generated using UAV tilt photogrammetry images. The segmentation effects of three deep learning models, PointNet++, MinkowskiNet and FPConv, on Shatangju trees and the ground were compared. The following three volume algorithms: convex hull by slices, voxel-based method and 3D convex hull were applied to calculate the volume of Shatangju trees. Model accuracy was evaluated using the coefficient of determination (R2) and Root Mean Square Error (RMSE). The results show that the overall accuracy of the MinkowskiNet model (94.57%) is higher than the other two models, which indicates the best segmentation effect. The 3D convex hull algorithm received the highest R2 (0.8215) and the lowest RMSE (0.3186 m3) for the canopy volume calculation, which best reflects the real volume of Citrus reticulate Blanco cv. Shatangju trees. The proposed method is capable of rapid and automatic acquisition for the canopy volume of Citrus reticulate Blanco cv. Shatangju trees.

show abstract

“…A new convolution operator learned from relationships in RS-CNN [ 49 ] is called relational shape convolution, which can encode the geometric relationship of points and expand the configuration of regular grid CNNs to achieve context-aware learning of point clouds. FPConv [ 50 ] proposed the surface style convolution operator. The operator disperses the convolution weight of each point along the local surface, so it is robust to input data.…”

Section: Related Workmentioning

confidence: 99%

Point Cloud Semantic Segmentation Network Based on Multi-Scale Feature Fusion

Jiang

Huang

et al. 2021

Sensors

View full text Add to dashboard Cite

The semantic segmentation of small objects in point clouds is currently one of the most demanding tasks in photogrammetry and remote sensing applications. Multi-resolution feature extraction and fusion can significantly enhance the ability of object classification and segmentation, so it is widely used in the image field. For this motivation, we propose a point cloud semantic segmentation network based on multi-scale feature fusion (MSSCN) to aggregate the feature of a point cloud with different densities and improve the performance of semantic segmentation. In our method, random downsampling is first applied to obtain point clouds of different densities. A Spatial Aggregation Net (SAN) is then employed as the backbone network to extract local features from these point clouds, followed by concatenation of the extracted feature descriptors at different scales. Finally, a loss function is used to combine the different semantic information from point clouds of different densities for network optimization. Experiments were conducted on the S3DIS and ScanNet datasets, and our MSSCN achieved accuracies of 89.80% and 86.3%, respectively, on these datasets. Our method showed better performance than the recent methods PointNet, PointNet++, PointCNN, PointSIFT, and SAN.

show abstract

FPConv: Learning Local Flattening for Point Convolution

Cited by 135 publications

References 35 publications

A Lightweight Structure Based on Feature Fusion for Point Cloud Analysis

A Lightweight Structure Based on Feature Fusion for Point Cloud Analysis

Canopy Volume Extraction of Citrus reticulate Blanco cv. Shatangju Trees Using UAV Image-Based Point Cloud Deep Learning

Point Cloud Semantic Segmentation Network Based on Multi-Scale Feature Fusion

Contact Info

Product

Resources

About