Papers › MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

MatrixVT: Efficient Multi-Camera to BEV Transformation for 3D Perception

19 Nov 2022ICCV 2023 1arXiv:2211.10593archive 2025-07-28

HongYu Zhou, Zheng Ge, Zeming Li, Xiangyu Zhang

This paper proposes an efficient multi-camera to Bird's-Eye-View (BEV) view transformation method for 3D perception, dubbed MatrixVT. Existing view transformers either suffer from poor transformation efficiency or rely on device-specific operators, hindering the broad application of BEV models. In contrast, our method generates BEV features efficiently with only convolutions and matrix multiplications (MatMul). Specifically, we propose describing the BEV feature as the MatMul of image feature and a sparse Feature Transporting Matrix (FTM). A Prime Extraction module is then introduced to compress the dimension of image features and reduce FTM's sparsity. Moreover, we propose the Ring \& Ray Decomposition to replace the FTM with two matrices and reformulate our pipeline to reduce calculation further. Compared to existing methods, MatrixVT enjoys a faster speed and less memory footprint while remaining deploy-friendly. Extensive experiments on the nuScenes benchmark demonstrate that our method is highly efficient but obtains results on par with the SOTA method in object detection and map segmentation tasks

PaperPDFConference PDFCode

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

Code

ZRandomize/MatrixVT officialmentioned on GitHubpytorchMIT report
megvii-basedetection/bevdepth mentioned on GitHubpytorchMIT 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

Autonomous DrivingBird's-Eye View Semantic SegmentationObject Detectionobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Bird's-Eye View Semantic Segmentation nuScenes MatrixVT IoU lane - 224x480 - 100x100 at 0.5 44.8 #15 of 17 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

SPEED

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