AI Paper Atlas

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

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

Zhongyu Xia, ZhiWei Lin, Xinhao Wang, Yongtao Wang, Yun Xing, Shengxiang Qi, Nan Dong, Ming-Hsuan Yang

ECCV 2024 · Detection and segmentation › 3D detection and driving · approach: Multi-camera BEV detection · 18 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
use hybrid image encoding (large short-term + small long-term encoder) instead of increasing resolution (ablation)HENet · nuScenes val 3D detectionNDS: 59.2 -> 59.9Improved
ensemble two baselines by NMS instead of hybrid encoding (ablation)BEVDepth4D + BEVStereo · nuScenes val 3D detectionNDS: 57.3 vs 59.9 (HENet)Hurt
add AFFM temporal integration (ablation)HENet · nuScenes val 3D detectionNDS: 59.2 -> 59.9Improved
add AFFM temporal integration (ablation)HENet · nuScenes val multi-taskBEV seg mIoU: 56.9 -> 58.0Improved
use adjacent frame attention instead of global attention (ablation)BEVDepth4D temporal fusion · nuScenes valNDS: 52.6 -> 53.1Improved
use attention-based AFFM instead of concatenation and convolution (ablation)BEVDepth4D temporal fusion · nuScenes valNDS: 52.8 -> 53.2Improved
add backward pass to forward AFFM (ablation)BEVDepth4D temporal fusion · nuScenes valmAP: 41.2 -> 41.5Improved
use a larger BEV encoder in place of AFFM (ablation)BEVDepth4D temporal fusion · nuScenes valNDS: 52.3 -> 52.4No clear effect
use a larger BEV grid (0.8m) for both tasks (ablation)multi-task BEVDepth4D · nuScenes valNDS / mIoU: NDS 53.2 -> 50.5; mIoU 41.6 -> 50.9Mixed
use 0.4m grid for detection and 0.8m grid for segmentation (ablation)multi-task BEVDepth4D · nuScenes valmIoU: 41.6 -> 50.6Improved
add adaptive feature selection (ablation)multi-task BEVDepth4D · nuScenes valNDS: 52.9 -> 53.3Improved
add independent BEV encoder per task (ablation)multi-task BEVDepth4D · nuScenes valmIoU: 51.2 -> 54.0Improved

Later papers that compared with this method

1 later accepted paper reports HENet as a baseline in their results tables; 1 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 3 of 4 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