Robust 3D Object Detection

Description from the archive archive 2025-07-28.

Benchmarks archive 2025-07-28

2 leaderboard tables shown for this task, 2 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

2 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

16 shown of 16 papers with code (33 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.

• PointPillars: Fast Encoders for Object Detection from Point Clouds
  14 Dec 2018 18 repositories listed Syntology ran 2 of 15 samples · 13 unverified · 1 pointer-only (licence)
  These benchmarks suggest that PointPillars is an appropriate encoding for object detection in point clouds.
• Center-based 3D Object Detection and Tracking
  19 Jun 2020 13 repositories listed Syntology ran 7 of 22 samples · 15 unverified
  Three-dimensional objects are commonly represented as 3D boxes in a point-cloud.
• PointRCNN: 3D Object Proposal Generation and Detection from Point Cloud
  11 Dec 2018 13 repositories listed Syntology ran 5 of 9 samples · 4 unverified · 4 pointer-only (licence)
  In this paper, we propose PointRCNN for 3D object detection from raw point cloud.
• PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection
  31 Dec 2019 12 repositories listed Syntology ran 2 of 16 samples · 14 unverified
  We present a novel and high-performance 3D object detection framework, named PointVoxel-RCNN (PV-RCNN), for accurate 3D object detection from point clouds.
• Cross Modal Transformer: Towards Fast and Robust 3D Object Detection
  3 Jan 2023 2 repositories listed
  In this paper, we propose a robust 3D detector, named Cross Modal Transformer (CMT), for end-to-end 3D multi-modal detection.
• TANet: Robust 3D Object Detection from Point Clouds with Triple Attention
  11 Dec 2019 2 repositories listed Syntology ran 0 of 3 samples · 3 unverified
  In this paper, we focus on exploring the robustness of the 3D object detection in point clouds, which has been rarely discussed in existing approaches.
• CRT-Fusion: Camera, Radar, Temporal Fusion Using Motion Information for 3D Object Detection
  5 Nov 2024 1 repository listed
  While recent radar-camera fusion methods have made significant progress by fusing information in the bird's-eye view (BEV) representation, they often struggle to effectively capture the motion of dynamic objects,…
• L4DR: LiDAR-4DRadar Fusion for Weather-Robust 3D Object Detection
  7 Aug 2024 1 repository listed Syntology ran 3 of 8 samples · 5 unverified
  However, the fusion of LiDAR and 4D radar is challenging because they differ significantly in terms of data quality and the degree of degradation in adverse weather.
• DiffuBox: Refining 3D Object Detection with Point Diffusion
  25 May 2024 1 repository listed Syntology ran 12 of 16 samples · 4 unverified · 16 pointer-only (licence)
  Ensuring robust 3D object detection and localization is crucial for many applications in robotics and autonomous driving.
• RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detection
  25 Mar 2024 1 repository listed
  In the dual-stream radar backbone, a point-based encoder and a transformer-based encoder are proposed to extract radar features, with an injection and extraction module to facilitate communication between the two…
• Sunshine to Rainstorm: Cross-Weather Knowledge Distillation for Robust 3D Object Detection
  28 Feb 2024 1 repository listed
  LiDAR-based 3D object detection models have traditionally struggled under rainy conditions due to the degraded and noisy scanning signals.
• Towards Robust 3D Object Detection with LiDAR and 4D Radar Fusion in Various Weather Conditions
  1 Jan 2024 1 repository listed
  Detecting objects in 3D under various (normal and adverse) weather conditions is essential for safe autonomous driving systems.
• Robust 3D Object Detection from LiDAR-Radar Point Clouds via Cross-Modal Feature Augmentation
  29 Sep 2023 1 repository listed Syntology ran 2 of 6 samples · 4 unverified · 6 pointer-only (licence)
  Specifically, spatial alignment is proposed to deal with the geometry discrepancy for better instance matching between LiDAR and radar.
• 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.
• 3D Dual-Fusion: Dual-Domain Dual-Query Camera-LiDAR Fusion for 3D Object Detection
  24 Nov 2022 1 repository listed
  Fusing data from cameras and LiDAR sensors is an essential technique to achieve robust 3D object detection.
• LiDAR Snowfall Simulation for Robust 3D Object Detection
  28 Mar 2022 1 repository listed
  Due to the difficulty of collecting and annotating training data in this setting, we propose a physically based method to simulate the effect of snowfall on real clear-weather LiDAR point clouds.

Syntology lines on 8 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.