AI Paper Atlas

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

Visual-Inertial-Semantic Scene Representation for 3D Object Detection

Jingming Dong, Xiaohan Fei, Stefano Soatto

CVPR 2017 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 51 citations (OpenAlex)

Check 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
Aggregate temporal evidence using the filter state from the last time each object was seen (Ours-FNL rather than Ours-INST)Visual-Inertial-Semantic Scene Representation · KITTI#TP: Ours-INST: 149 -> Ours-FNL: 169 (position error <0.5 m; orientation ignored); Ours-INST: 320 -> Ours-FNL: 425 (position Improved
Use the current-time filter estimate (Ours-INST) instead of single-frame SubCNN detectionsVisual-Inertial-Semantic Scene Representation · KITTI#TP: 99 -> 149 (position error <0.5 m; orientation ignored)Improved
Apply class-specific size and shape priorsVisual-Inertial-Semantic Scene Representation · KITTI toy-car exampletoy car rejectionImproved
Use a co-occurrence prior to rebalance class evidenceVisual-Inertial-Semantic Scene Representation · Pascal VOC2012 co-occurrence examplesclass evidenceNo clear effect

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