Papers › Embracing Single Stride 3D Object Detector with Sparse Transformer

Embracing Single Stride 3D Object Detector with Sparse Transformer

13 Dec 2021CVPR 2022 1arXiv:2112.06375archive 2025-07-28

Lue Fan, Ziqi Pang, Tianyuan Zhang, Yu-Xiong Wang, Hang Zhao, Feng Wang, Naiyan Wang, Zhaoxiang Zhang

In LiDAR-based 3D object detection for autonomous driving, the ratio of the object size to input scene size is significantly smaller compared to 2D detection cases. Overlooking this difference, many 3D detectors directly follow the common practice of 2D detectors, which downsample the feature maps even after quantizing the point clouds. In this paper, we start by rethinking how such multi-stride stereotype affects the LiDAR-based 3D object detectors. Our experiments point out that the downsampling operations bring few advantages, and lead to inevitable information loss. To remedy this issue, we propose Single-stride Sparse Transformer (SST) to maintain the original resolution from the beginning to the end of the network. Armed with transformers, our method addresses the problem of insufficient receptive field in single-stride architectures. It also cooperates well with the sparsity of point clouds and naturally avoids expensive computation. Eventually, our SST achieves state-of-the-art results on the large scale Waymo Open Dataset. It is worth mentioning that our method can achieve exciting performance (83.8 LEVEL 1 AP on validation split) on small object (pedestrian) detection due to the characteristic of single stride. Codes will be released at https://github.com/TuSimple/SST

Paper PDF Conference PDF Code

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

tusimple/sst officialmentioned in papermentioned on GitHubpytorchApache-2.0 report

tusen-ai/sst mentioned on GitHubpytorchApache-2.0 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

3D Object Detection Autonomous Driving Object Object Detection Pedestrian Detection object-detection

Results from the paper archive 2025-07-28

Task	Dataset	Model	Metric	Value	Rank at snapshot	Leaderboard	Report
3D Object Detection	waymo cyclist	SST	APH/L2	72.17	#3 of 7	Archive leaderboard	report
3D Object Detection	waymo pedestrian	SST	APH/L2	73.51	#4 of 7	Archive leaderboard	report
3D Object Detection	waymo vehicle	SST	APH/L2	72.74	#5 of 8	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 Encodings Adam Attention Attention Dropout BPE Cosine Annealing Dense Connections Dropout Label Smoothing Layer Normalization Linear Layer Linear Warmup With Cosine Annealing Multi-Head Attention Position-Wise Feed-Forward Layer Residual Connection Softmax Sparse Transformer Transformer Weight Decay

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