AI Paper Atlas

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

Recognizing Objects From Any View With Object and Viewer-Centered Representations

Sainan Liu, Vincent Nguyen, Isaac Rehg, Zhuowen Tu

CVPR 2020 · Detection and segmentation › 3D detection and driving · approach: 3D objectness and scene segmentation · 4 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
Combine object-centered and viewer-centered branchesOVCNet · gMIRO SeenInstancesaccuracy overall (%): 68.34 -> 73.24Improved
Combine object-centered and viewer-centered branchesOVCNet · gMIRO NovelInstancesaccuracy overall (%): 53.27 -> 65.85Improved
Add object-centered, VC (3D), and VC (2D) branches together (ablation)OVCNet · gMIVO SeenInstancesaccuracy (%): 63.66 -> 79.36Improved
Add object-centered, VC (3D), and VC (2D) branches together (ablation)OVCNet · gMIVO NovelInstancesaccuracy (%): 64.50 -> 75.33Improved
Add the ancillary spherical pathway integrating VC (3D) features (ablation)OC module · gMIRO SeenInstancesaccuracy overall (%): 44.62 ± 0.58 -> 54.62 ± 0.73Improved
Add texture spherical-map information (ablation)GenRe + spherical CNNs (bw=112) · gMIRO SeenInstancesaccuracy overall (%): 42.43 ± 1.24 -> 44.62 ± 0.58Improved
Increase spherical CNN bandwidth from 60 to 112 (ablation)GenRe + spherical CNNs · gMIRO SeenInstancesaccuracy overall (%): 40.79 ± 1.21 -> 42.43 ± 1.24Improved
Increase spherical CNN bandwidth from 112 to 128 (ablation)GenRe + spherical CNNs · gMIRO SeenInstancesaccuracy overall (%): 42.43 ± 1.24 -> 40.94 ± 1.88Hurt
Increase voxel resolution from 30×30×30 to 128×128×128 (ablation)GenRe + 3D CNNs · gMIRO SeenInstancesaccuracy overall (%): 20.94 ± 0.41 -> 30.26 ± 0.62Improved
Increase 3D viewpoint augmentations from 1 to 160 (ablation)GenRe + ResNet18 · gMIRO SeenInstancesaccuracy overall (%): 32.49 ± 0.68 -> 45.15 ± 0.46Improved
Increase 3D viewpoint augmentations from 160 to 640 (ablation)GenRe + ResNet18 · gMIRO SeenInstancesaccuracy overall (%): 45.15 ± 0.46 -> 51.24 ± 0.23Improved
Use 30-degree rather than denser in-plane rotation augmentation (ablation)VC (2D) ResNet18 · gMIROaccuracyNo 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