AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

UniTR: A Unified and Efficient Multi-Modal Transformer for Bird's-Eye-View Representation

Haiyang Wang, Hao Tang, Shaoshuai Shi, Aoxue Li, Zhenguo Li, Bernt Schiele, Liwei Wang

ICCV 2023 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 120 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add camera image 2D perspective-space cross-modal fusion to lidar-only model (ablation)UniTR · nuScenes valNDS: 70.5 -> 72.5Improved
add 3D geometric-space cross-modal fusion to lidar-only model (ablation)UniTR · nuScenes valNDS: 70.5 -> 72.0Improved
combine 2D and 3D fusion spaces (ablation)UniTR · nuScenes valNDS / mAP: 70.5 -> 73.1 NDS, 65.9 -> 70.0 mAPImproved
add BEV LSS fusion step (ablation)UniTR · nuScenes valNDS: 73.1 -> 73.3Improved
parallel weight-sharing intra-modal block instead of serial modality-specific encoders (ablation)UniTR · nuScenes vallatency (ms): 51 -> 33Improved
parallel weight-sharing instead of serial (ablation)UniTR · nuScenes valNDS: 72.2 -> 72.4Improved
place inter-modal blocks before intra-modal block (ablation)UniTR · nuScenes valNDS: 73.3 -> 72.9Hurt
order 3D fusion before 2D fusion (ablation)UniTR · nuScenes valNDS: 73.3 -> 73.0Hurt
parallel instead of serial processing under low-beam LiDAR (1-beam) (ablation)UniTR · nuScenes val 1-beam LiDAR + cameraNDS: 57.6 -> 59.5Improved
parallel instead of serial processing with 32-beam LiDAR (ablation)UniTR · nuScenes val 32-beam LiDAR + cameraNDS: 73.2 -> 73.3No clear effect
replace modality-specific encoders and late fusion with unified UniTR backboneBEVFusion framework · nuScenes val 3D detectionNDS / latency: 71.4 -> 73.1 NDS; 130.5 -> 88.7 msImproved
UniTR lidar-only variant versus prior lidar methods on BEV segmentationUniTR · nuScenes val BEV map segmentationmean IoU: 48.6 -> 71.2 (vs CenterPoint)Improved

Later papers that compared with this method

6 later accepted papers report UniTR as a baseline in their results tables; 5 of them report a better number on most of the results they share with it.

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy