AI Paper Atlas

Research map / Point clouds / Segmentation and detection

MSF: Motion-Guided Sequential Fusion for Efficient 3D Object Detection From Point Cloud Sequences

Chenhang He, Ruihuang Li, Yabin Zhang, Shuai Li, Lei Zhang

CVPR 2023 · Point clouds › Segmentation and detection · approach: Multimodal and open-vocabulary 3D detection · 29 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
propagate current-frame proposals using estimated motion and fuse sequential pointsMSF · Waymo Open Dataset test3D mAPH L1: 80.91 -> 81.74Improved
add Motion Embedding (ablation)MSF · Waymo Open Dataset validationAPH L1: 80.03 -> 80.20; +0.17Improved
add Motion Embedding (ablation)MSF · Waymo Open Dataset validationAPH L2: 74.50 -> 74.62; +0.12Improved
add Self-Attention for intra-proposal spatial interactions (ablation)MSF · Waymo Open Dataset validationAPH L1: 76.51 -> 80.20; +3.69Improved
add Self-Attention for intra-proposal spatial interactions (ablation)MSF · Waymo Open Dataset validationAPH L2: 71.91 -> 74.62; +2.71Improved
add BiFA cross-frame aggregation (ablation)MSF · Waymo Open Dataset validationAPH L1: 78.25 -> 80.20; +1.95Improved
add BiFA cross-frame aggregation (ablation)MSF · Waymo Open Dataset validationAPH L2: 73.11 -> 74.62; +1.51Improved
use both forward and backward aggregation paths rather than forward-only aggregation (ablation)MSF · Waymo Open Dataset validationAPH L1: 79.64 -> 80.20; +0.56Improved
use both forward and backward aggregation paths rather than backward-only aggregation (ablation)MSF · Waymo Open Dataset validationAPH L2: 73.77 -> 74.62; +0.85Improved
use a query-based decoder instead of single max-pooling (ablation)MSF · Waymo Open Dataset validationAPH L1: 79.54 -> 80.20; +0.66Improved
replace raw points with proxy points (ablation)MSF with Self-Attention · Waymo Open Dataset validation, Pedestrian L2APH: 75.11 -> 74.20; -0.91Hurt
replace raw points and Self-Attention with proxy points and MLP Mixer (ablation)MSF · Waymo Open Dataset validation, Vehicle L2APH: 73.35 -> 73.45; +0.10Improved

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