Research map / Detection and segmentation / 3D detection and driving
Gated3D: Monocular 3D Object Detection From Temporal Illumination Cues
Frank Julca-Aguilar, Jason Taylor, Mario Bijelic, Fahim Mannan, Ethan Tseng, Felix Heide
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 changed | Where | Measured | Effect |
|---|---|---|---|
| use gated images instead of RGB (M3D-RPN) at night | Gated3D · Gated3D test, Pedestrian, night, 50-80m | 3D AP: 2.07 -> 14.98 | Improved |
| use gated images instead of stereo (Stereo-RCNN) at long range | Gated3D · Gated3D test, Car, day, 50-80m | 3D AP: 6.17 -> 14.85 | Improved |
| use direct gated network instead of pseudo-lidar depth-map pipeline | Gated3D · Gated3D test, Pedestrian, day, 0-30m | 3D AP: 6.19 -> 50.94 | Improved |
| use direct gated network instead of PatchNet on gated images | Gated3D · Gated3D test, Car, day, 0-30m | 3D AP: 23.91 -> 52.15 | Improved |
| use gated input instead of stereo input at close range for cars | Gated3D · Gated3D test, Car, day, 0-30m | 3D AP: 54.17 -> 52.15 | No clear effect |
| use gated input instead of stereo input for pedestrians at 30-50m | Gated3D · Gated3D test, Pedestrian, day, 30-50m | 3D AP: 23.26 -> 20.59 | Hurt |
| use gated 3D detector instead of lidar PointPillars for far pedestrians | Gated3D · Gated3D test, Pedestrian, day, 50-80m | 3D AP: 0.00 -> 14.14 | Improved |
| use gated 3D detector instead of lidar PointPillars for near cars | Gated3D · Gated3D test, Car, day, 0-30m | 3D AP: 91.51 -> 52.15 | Hurt |
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.
- M3D-RPN — M3D-RPN: Monocular 3D Region Proposal Network for Object Detection (ICCV 2019) · better on 11 of 12 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
- MonoDistill: Learning Spatial Features for Monocular 3D Object Detection (ICLR 2022 · similarity 0.90)
- MonoDETR: Depth-guided Transformer for Monocular 3D Object Detection (ICCV 2023 · similarity 0.89)
- LeAD-M3D: Leveraging Asymmetric Distillation for Real-Time Monocular 3D Detection (ECCV 2026 · similarity 0.89)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.88)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.88)
- FD3D: Exploiting Foreground Depth Map for Feature-Supervised Monocular 3D Object Detection (AAAI 2024 · similarity 0.87)
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.
