AI Paper Atlas

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

3D Object Proposals Using Stereo Imagery for Accurate Object Class Detection

Xiaozhi Chen, Kaustav Kundu, Yukun Zhu, Huimin Ma, Sanja Fidler, Raquel Urtasun

TPAMI 2017 · Detection and segmentation › 3D detection and driving · approach: Depth-based and label-free 3D detection · 433 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 orientation regression loss (ablation)detection network · KITTI val Cars ModerateAOS: 38.24 -> 85.80Improved
add orientation regression loss (ablation)detection network · KITTI val Cars ModerateAP_2D: 87.26 -> 87.52No clear effect
add contextual branch (ablation)detection network · KITTI val Cars ModerateAP_2D: 87.52 -> 88.07Improved
add contextual branch (ablation)detection network · KITTI val Pedestrians ModerateAP_2D: 69.42 -> 64.46Hurt
add class-specific weights in proposal generation (ablation)detection network · KITTI val Cars ModerateAP_2D: 87.30 -> 88.07Improved
use class-specific proposals instead of class-independent variant (ablation)proposal generation · KITTI 2D box recallrecallImproved
replace Selective Search proposals with ours (ablation)detection network · KITTI val Cars ModerateAP_2D: 60.00 -> 88.07Improved
replace EdgeBoxes proposals with ours (ablation)detection network · KITTI val Cars ModerateAP_2D: 70.47 -> 88.07Improved
add HHA depth stream (two-stream RGB-HHA) (ablation)detection network, hybrid data · KITTI val Cars ModerateAP_3D: 75.86 -> 81.21Improved
add HHA depth stream (two-stream RGB-HHA) (ablation)detection network, stereo data · KITTI val Cars ModerateAP_3D: 56.97 -> 68.90Improved
add HHA depth stream (ablation)detection network · KITTI val CarsAP_2DNo clear effect
use LIDAR instead of stereo proposals (ablation)proposal generation · KITTI val Cars ModerateAP_3D: 69.52 -> 73.56Improved

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