AI Paper Atlas

Research map / Point clouds / Segmentation and detection

EPMF: Efficient Perception-Aware Multi-Sensor Fusion for 3D Semantic Segmentation

Mingkui Tan, Zhuangwei Zhuang, Sitao Chen, Rong Li, Kui Jia, Qicheng Wang, Yuanqing Li

TPAMI 2024 · Point clouds › Segmentation and detection · approach: LiDAR segmentation for driving · 54 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 perspective projection (vs spherical) with LiDAR-only input (ablation)SalsaNext baseline · SemanticKITTI-FV valmIoU: 57.2 -> 57.6Improved
add perspective projection (vs spherical) in multimodal fusion (ablation)PMF · SemanticKITTI-FV valmIoU: 55.8 -> 61.7Improved
add ASPP to LiDAR stream (ablation)PMF · SemanticKITTI-FV valmIoU: 57.6 -> 59.7Improved
add residual-based fusion modules (ablation)PMF · SemanticKITTI-FV valmIoU: 59.7 -> 61.7Improved
add perception-aware loss (ablation)PMF · SemanticKITTI-FV valmIoU: 61.7 -> 63.9Improved
drop the decoder of the camera stream (ablation)PMF · SemanticKITTI-FV valmIoU: 63.9 -> 63.9No clear effect
add cross-modal alignment and crop (ablation)PMF · SemanticKITTI-FV valFLOPs: 854.7 G -> 739.9 GImproved
add improved contextual module (ablation)EPMF · SemanticKITTI-FV valmIoU: 63.9 -> 64.8Improved
fuse high-level LiDAR features into camera stream (ablation)EPMF · SemanticKITTI-FV valmIoU: 64.8 -> 65.9Improved
mask 10% of image from bottom (no fine-tuning) (ablation)EPMF · SemanticKITTI-FV valmIoU: 65.9 -> 65.5Hurt
mask 50% of image (no fine-tuning) (ablation)EPMF · SemanticKITTI-FV valmIoU: 65.9 -> 54.8Hurt
fine-tune with image masks at 50% masked ratio (ablation)EPMF · SemanticKITTI-FV valmIoU: 54.8 -> 60.6Improved

Later papers that compared with this method

1 later accepted paper reports EPMF 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 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