Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
Open accessThe DOI matches its Crossref record; 55 of the 55 references it cites were found in a registry or an index.
Abstract
State-of-the-art methods for large-scale driving-scene LiDAR segmentation often project the point clouds to 2D space and then process them via 2D convolution. Although this corporation shows the competitiveness in the point cloud, it inevitably alters and abandons the 3D topology and geometric relations. A natural remedy is to utilize the 3D voxelization and 3D convolution network. However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited. An important reason is the property of the outdoor point cloud, namely sparsity and varying density. Motivated by this investigation, we propose a new framework for the outdoor LiDAR segmentation, where cylindrical partition and asymmetrical 3D convolution networks are designed to explore the 3D geometric pattern while maintaining these inherent properties. Moreover, a point-wise refinement module is introduced to alleviate the interference of lossy voxel-based label encoding. We evaluate the proposed model on two large-scale datasets, i.e., SemanticKITTI and nuScenes. Our method achieves the 1st place in the leaderboard of SemanticKITTI and outperforms existing methods on nuScenes with a noticeable margin, about 4%. Furthermore, the proposed 3D framework also generalizes well to LiDAR panoptic segmentation and LiDAR 3D detection.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Fully convolutional networks for semantic segmentation
Long, J., Shelhamer, E., & Darrell, T. (2015) · 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2015.7298965 · Cited by 38,834
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2016) · arXiv · doi:10.48550/arxiv.1606.00915 · Cited by 22,392
Chen, L.-C., Papandreou, G., Kokkinos, I., Murphy, K., & Yuille, A. L. (2018) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2017.2699184 · Cited by 22,392
Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · arXiv · doi:10.48550/arxiv.1802.02611 · Cited by 20,063 · cited 1×
“Built upon the FCN, many works aim to improve the performance via exploring the dilated convolution, multi-scale context modeling and attention modeling, including DeepLab[6, 7] and PSP [52].”
MethodEncoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation
Chen, L.-C., Zhu, Y., Papandreou, G., Schroff, F., & Adam, H. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-01234-2_49 · Cited by 20,054
Veličković, P., Cucurull, G., Casanova, A., Romero, A., Liò, P., & Bengio, Y. (2017) · arXiv · doi:10.48550/arxiv.1710.10903 · Cited by 12,107
PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
Charles, R. Q., Su, H., Kaichun, M., & Guibas, L. J. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.16 · Cited by 9,237
Veličković, P., Casanova, A., Liò, P., Cucurull, G., Romero, A., & Bengio, Y. (2017) · arXiv (Cornell University) · doi:10.17863/cam.48429 · Cited by 8,657
3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation
Çiçek, Ö., Abdulkadir, A., Lienkamp, S. S., Brox, T., & Ronneberger, O. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46723-8_49 · Cited by 7,945 · cited 3×
“However, in our initial attempts, we directly apply the 3D voxelization [14, 9] and 3D convolution networks to outdoor LiDAR point cloud, only to find very limited performance gain (as shown in Fig.”
BackgroundMethodInfluentialDynamic Graph CNN for Learning on Point Clouds
Wang, Y., Sun, Y., Liu, Z., Sarma, S. E., Bronstein, M. M., & Solomon, J. M. (2019) · ACM Transactions on Graphics · doi:10.1145/3326362 · Cited by 7,199
Cited by
FCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Wang, T., Zhu, X., Pang, J., & Lin, D. (2021) · arXiv · doi:10.48550/arxiv.2104.10956 · Cited by 683
Self-citationFCOS3D: Fully Convolutional One-Stage Monocular 3D Object Detection
Wang, T., Zhu, X., Pang, J., & Lin, D. (2021) · 2021 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW) · doi:10.1109/iccvw54120.2021.00107 · Cited by 683
“Most state-of-the-art methods [38, 14, 29, 32, 40, 41] rely on the accurate 3D information provided by LiDAR point clouds, but it is a heavy burden to install expensive LiDARs on each vehicle.”
MethodSelf-citationPoint Transformer V3: Simpler, Faster, Stronger
Wu, X., Jiang, L., Wang, P.-S., Liu, Z., Liu, X., Qiao, Y., Ouyang, W., He, T., & Zhao, H. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00463 · Cited by 648
OccWorld: Learning a 3D Occupancy World Model for Autonomous Driving
Zheng, W., Chen, W., Huang, Y., Zhang, B., Duan, Y., & Lu, J. (2023) · arXiv · doi:10.48550/arxiv.2311.16038 · Cited by 342
RPVNet: A Deep and Efficient Range-Point-Voxel Fusion Network for LiDAR Point Cloud Segmentation
Xu, J., Zhang, R., Dou, J., Zhu, Y., Sun, J., & Pu, S. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01572 · Cited by 336
Tri-Perspective View for Vision-Based 3D Semantic Occupancy Prediction
Huang, Y., Zheng, W., Zhang, Y., Zhou, J., & Lu, J. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.00890 · Cited by 312
2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
Yan, X., Gao, J., Zheng, C., Zheng, C., Zhang, R., Cui, S., & Li, Z. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-19815-1_39 · Cited by 280
SurroundOcc: Multi-Camera 3D Occupancy Prediction for Autonomous Driving
Wei, Y., Zhao, L., Zheng, W., Zhu, Z., Zhou, J., & Lu, J. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01986 · Cited by 260
Perception-Aware Multi-Sensor Fusion for 3D LiDAR Semantic Segmentation
Zhuang, Z., Li, R., Jia, K., Wang, Q., Li, Y., & Tan, M. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01597 · Cited by 216
Recent Advancements in Learning Algorithms for Point Clouds: An Updated Overview
Camuffo, E., Mari, D., & Milani, S. (2022) · Sensors · doi:10.3390/s22041357 · Cited by 73
“More recently, Cylinder3D [77] (Figure 10) was introduced in the context of automotive point clouds for driving-scene modeling.”
BackgroundRizzoli, G., Barbato, F., & Zanuttigh, P. (2022) · Technologies · doi:10.3390/technologies10040090 · Cited by 58
Multi-Sem Fusion: Multimodal Semantic Fusion for 3-D Object Detection
Xu, S., Li, F., Song, Z., Fang, J., Wang, S., & Yang, Z.-X. (2024) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2024.3387732 · Cited by 26
“Implementation Details HTCNet [50] and Cylinder3D [62] are employed here for obtaining the 2D and 3D semantic segmentation results respectively.”
Method
Metadata
- Authors
- Zhu, X., Zhou, H., Wang, T., Hong, F., Ma, Y., Li, W., Li, H., & Lin, D.
- Venue
- 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2021-06
- Pages
- 9934-9943
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W3177330511
- Cited by
- 623
- References
- 55
- FWCI
- 36.30
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.