Robust 3D Semantic Segmentation

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

3 leaderboard tables shown for this task, 3 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.

Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. A dash means no Syntology record for that paper, not a recorded non-run. Read from the graph 2026-09-24.

Libraries

Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.

Datasets archive 2025-07-28

3 datasets whose archive record lists this task, ordered by the archive's paper count.

Subtasks archive 2025-07-28

No subtask under this task in the archive's task tree.

Parent tasks archive 2025-07-28

Most implemented papers archive 2025-07-28

17 shown of 17 papers with code (19 tagged with this task in all), ordered by repositories listed in the archive, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers without a page here are shown as plain text.

• KPConv: Flexible and Deformable Convolution for Point Clouds
  18 Apr 2019 10 repositories listed Syntology ran 5 of 12 samples · 7 unverified · 3 pointer-only (licence)
  Furthermore, these locations are continuous in space and can be learned by the network.
• 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks
  18 Apr 2019 8 repositories listed Syntology ran 1 of 2 samples · 1 unverified · 2 pointer-only (licence)
  To overcome challenges in the 4D space, we propose the hybrid kernel, a special case of the generalized sparse convolution, and the trilateral-stationary conditional random field that enforces spatio-temporal…
• Searching Efficient 3D Architectures with Sparse Point-Voxel Convolution
  31 Jul 2020 6 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  Self-driving cars need to understand 3D scenes efficiently and accurately in order to drive safely.
• SalsaNext: Fast, Uncertainty-aware Semantic Segmentation of LiDAR Point Clouds for Autonomous Driving
  7 Mar 2020 5 repositories listed Syntology ran 4 of 11 samples · 7 unverified · 1 pointer-only (licence)
  In this paper, we introduce SalsaNext for the uncertainty-aware semantic segmentation of a full 3D LiDAR point cloud in real-time.
• SqueezeSeg: Convolutional Neural Nets with Recurrent CRF for Real-Time Road-Object Segmentation from 3D LiDAR Point Cloud
  19 Oct 2017 5 repositories listed Syntology ran 0 of 7 samples · 7 unverified
  In this paper, we address semantic segmentation of road-objects from 3D LiDAR point clouds.
• PolarNet: An Improved Grid Representation for Online LiDAR Point Clouds Semantic Segmentation
  31 Mar 2020 4 repositories listed Syntology ran 9 of 11 samples · 2 unverified · 1 pointer-only (licence)
  The need for fine-grained perception in autonomous driving systems has resulted in recently increased research on online semantic segmentation of single-scan LiDAR.
• CENet: Toward Concise and Efficient LiDAR Semantic Segmentation for Autonomous Driving
  26 Jul 2022 3 repositories listed Syntology ran 0 of 1 samples · 1 unverified
  Accurate and fast scene understanding is one of the challenging task for autonomous driving, which requires to take full advantage of LiDAR point clouds for semantic segmentation.
• CPGNet: Cascade Point-Grid Fusion Network for Real-Time LiDAR Semantic Segmentation
  21 Apr 2022 3 repositories listed Syntology ran 1 of 4 samples · 3 unverified
  LiDAR semantic segmentation essential for advanced autonomous driving is required to be accurate, fast, and easy-deployed on mobile platforms.
• Cylindrical and Asymmetrical 3D Convolution Networks for LiDAR Segmentation
  19 Nov 2020 2 repositories listed
  However, we found that in the outdoor point cloud, the improvement obtained in this way is quite limited.
• RangeNet++: Fast and Accurate LiDAR Semantic Segmentation
  4 Nov 2019 2 repositories listed
  Perception in autonomous vehicles is often carried out through a suite of different sensing modalities.
• Robo3D: Towards Robust and Reliable 3D Perception against Corruptions
  30 Mar 2023 1 repository listed
  The robustness of 3D perception systems under natural corruptions from environments and sensors is pivotal for safety-critical applications.
• Using a Waffle Iron for Automotive Point Cloud Semantic Segmentation
  24 Jan 2023 1 repository listed Syntology ran 5 of 5 samples · 0 unverified · 5 pointer-only (licence)
  Semantic segmentation of point clouds in autonomous driving datasets requires techniques that can process large numbers of points efficiently.
• PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud
  28 Nov 2022 1 repository listed
  In this work, we establish PIDS, a novel paradigm to jointly explore point interactions and point dimensions to serve semantic segmentation on point cloud data.
• 2DPASS: 2D Priors Assisted Semantic Segmentation on LiDAR Point Clouds
  10 Jul 2022 1 repository listed
  As camera and LiDAR sensors capture complementary information used in autonomous driving, great efforts have been made to develop semantic segmentation algorithms through multi-modality data fusion.
• GFNet: Geometric Flow Network for 3D Point Cloud Semantic Segmentation
  6 Jul 2022 1 repository listed
  However, recent projection-based methods for point cloud semantic segmentation usually utilize a vanilla late fusion strategy for the predictions of different views, failing to explore the complementary information from…
• FIDNet: LiDAR Point Cloud Semantic Segmentation with Fully Interpolation Decoding
  8 Sep 2021 1 repository listed
  In this paper, we propose a new projection-based LiDAR semantic segmentation pipeline that consists of a novel network structure and an efficient post-processing step.
• SqueezeSegV2: Improved Model Structure and Unsupervised Domain Adaptation for Road-Object Segmentation from a LiDAR Point Cloud
  22 Sep 2018 1 repository listed Syntology ran 0 of 4 samples · 4 unverified
  When training our new model on synthetic data using the proposed domain adaptation pipeline, we nearly double test accuracy on real-world data, from 29.

Syntology lines on 10 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced. Read from the graph 2026-09-24.