Pith. sign in

REVIEW 4 cited by

Efficient and Robust 2D-to-BEV Representation Learning via Geometry-guided Kernel Transformer

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2206.04584 v1 pith:VFH6ZTNG submitted 2022-06-09 cs.CV

Shaoyu Chen , Tianheng Cheng , Xinggang Wang , Wenming Meng , Qian Zhang , Wenyu Liu This is my paper
classification cs.CV
keywords representationkernellearningtransformercamerad-to-bevgeometry-guidedgreat
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Learning Bird's Eye View (BEV) representation from surrounding-view cameras is of great importance for autonomous driving. In this work, we propose a Geometry-guided Kernel Transformer (GKT), a novel 2D-to-BEV representation learning mechanism. GKT leverages the geometric priors to guide the transformer to focus on discriminative regions and unfolds kernel features to generate BEV representation. For fast inference, we further introduce a look-up table (LUT) indexing method to get rid of the camera's calibrated parameters at runtime. GKT can run at $72.3$ FPS on 3090 GPU / $45.6$ FPS on 2080ti GPU and is robust to the camera deviation and the predefined BEV height. And GKT achieves the state-of-the-art real-time segmentation results, i.e., 38.0 mIoU (100m$\times$100m perception range at a 0.5m resolution) on the nuScenes val set. Given the efficiency, effectiveness, and robustness, GKT has great practical values in autopilot scenarios, especially for real-time running systems. Code and models will be available at \url{https://github.com/hustvl/GKT}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Unified Modeling of Lane and Lane Topology for Driving Scene Reasoning

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    UniTopo unifies lane detection and topology reasoning into a single perception model, outperforming prior methods on OpenLane-V2 benchmarks with TOP_ll scores of 30.1% and 31.8%.

  2. TopoMaskV3: 3D Mask Head with Dense Offset and Height Predictions for Road Topology Understanding

    cs.CV 2026-03 unverdicted novelty 7.0 of 10

    TopoMaskV3 adds dense offset and height heads to produce standalone 3D road centerlines from masks and reports 28.5 OLS on a new geographically disjoint long-range benchmark.

  3. GaussianMap: Learning Gaussian Representation for Multi-Sensor Online HD Map Construction

    cs.CV 2026-06 unverdicted novelty 6.0 of 10

    GaussianMap learns adaptive Gaussian primitives on the BEV plane from multi-sensor data to produce vectorized HD maps, reporting state-of-the-art results on nuScenes and Argoverse 2.

  4. Mapping like a Skeptic: Probabilistic BEV Projection for Online HD Mapping

    cs.CV 2025-08 conditional novelty 6.0 of 10

    A probabilistic BEV projection with learned offsets and confidence-based temporal fusion improves online HD map accuracy and generalization.

Pith tools