Research map / Detection and segmentation / 3D detection and driving
Monocular 3D Object Detection with Bounding Box Denoising in 3D by Perceiver
Xianpeng Liu, Ce Zheng, Kelvin B Cheng, Nan Xue, Guo-Jun Qi, Tianfu Wu
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 |
|---|---|---|---|
| add RoI appearance features for proposal verification (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 19.01 -> 21.04 | Improved |
| add geometric embeddings (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 21.04 -> 21.67 | Improved |
| use Perceiver instead of MLP to fuse appearance and geometry (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 21.67 -> 22.40 | Improved |
| add rescoring head (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 19.01 -> 21.41 | Improved |
| add localization residual branch (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 21.41 -> 22.30 | Improved |
| add dimension residual branch (ablation) | MonoXiver on MonoCon · KITTI val Car (Moderate) | AP_3D: 22.30 -> 22.40 | Improved |
| apply MonoXiver to SMOKE backbone | SMOKE · KITTI val Car (Moderate) | AP_3D: 7.09 -> 9.40 | Improved |
| apply MonoXiver to MonoDLE backbone | MonoDLE · KITTI val Car (Moderate) | AP_3D: 13.72 -> 16.19 | Improved |
| apply MonoXiver to GUPNet and DEVIANT | GUPNet, DEVIANT · Waymo val Level_1 | AP_3D: GUPNet 10.02 -> 11.47; DEVIANT 10.98 -> 11.88 | Improved |
| add MonoXiver second stage (inference cost) | MonoCon · RTX5000 latency | latency (ms): 18 -> 25 | Hurt |
| use coarser sampling stride in oracle top-down grid (ablation) | oracle local-grid search on MonoCon anchors · KITTI val Car (Moderate) | AP_3D upper bound: 64.93 (stride 0.1, +-2) -> 34.44 (stride 0.75, +-1.5) | 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.
- DEVIANT — DEVIANT: Depth EquiVarIAnt NeTwork for Monocular 3D Object Detection (ECCV 2022) · better on 1 of 1 shared result
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
- Monocular 3D Object Detection Leveraging Accurate Proposals and Shape Reconstruction (CVPR 2019 · similarity 0.91)
- MonoDiff: Monocular 3D Object Detection and Pose Estimation with Diffusion Models (CVPR 2024 · similarity 0.90)
- MonoDGP: Monocular 3D Object Detection with Decoupled-Query and Geometry-Error Priors (CVPR 2025 · similarity 0.90)
- MonoMAE: Enhancing Monocular 3D Detection through Depth-Aware Masked Autoencoders (NeurIPS 2024 · similarity 0.90)
- MonoPlace3D: Learning 3D-Aware Object Placement for 3D Monocular Detection (CVPR 2025 · similarity 0.89)
- MonoCD: Monocular 3D Object Detection with Complementary Depths (CVPR 2024 · similarity 0.88)
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.
