Papers › A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic...

A Large-Scale Network Construction and Lightweighting Method for Point Cloud Semantic Segmentation

21 Mar 2024IEEE Transactions on Image Processing 2024 3archive 2025-07-28

Jiawei Han; Kaiqi Liu; Wei Li; Guangzhi Chen; Wenguang Wang; Feng Zhang

To significantly enhance the performance of point cloud semantic segmentation, this manuscript presents a novel method for constructing large-scale networks and offers an effective lightweighting technique. First, a latent point feature processing (LPFP) module is utilized to interconnect base networks such as PointNet++ and Point Transformer. This intermediate module serves both as a feature information transfer and a ground truth supervision function. Furthermore, in order to alleviate the increase in computational costs brought by constructing large-scale networks and better adapt to the demand for terminal deployment, a novel point cloud lightweighting method for semantic segmentation network (PCLN) is proposed to compress the network by transferring multidimensional feature information of large-scale networks. Specifically, at different stages of the large-scale network, the structure and attention information of the point features are selectively transferred to guide the compressed network to train in the direction of the large-scale network. This paper also solves the problem of representing global structure information of large-scale point clouds through feature sampling and aggregation. Extensive experiments on public datasets and real-world data demonstrate that the proposed method can significantly improve the performance of different base networks and outperform the state-of-the-art.

PaperPDFCode

Code

Javion11/PointLiBR officialpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Semantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Segmentation S3DIS Area5 LPFP(Point Transformer*) FLOPs 24.2G #10 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 LPFP(Point Transformer*) Number of params 31.2M #10 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 LPFP(Point Transformer*) mAcc 78.7 #10 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 LPFP(Point Transformer*) mIoU 73.5 #10 of 61 Archive leaderboard report
Semantic Segmentation S3DIS Area5 LPFP(Point Transformer*) oAcc 92.0 #10 of 61 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Absolute Position EncodingsAdamAttentionBASEBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections