Research map / Detection and segmentation / 3D detection and driving
ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 adaptive zooming to normalize instance resolution and adjust camera intrinsics (ablation) | ZoomNet · KITTI validation, Moderate | AP3d (IoU=0.7): 40.39 -> 50.47 | Helped |
| Add pixel-wise part locations (ablation) | ZoomNet · KITTI validation, Moderate | AP3d (IoU=0.7): 40.87 -> 50.47 | Helped |
| Add a 3D fitting score to the detection confidence (ablation) | ZoomNet · KITTI validation, Moderate | AP3d (IoU=0.7): 46.67 -> 50.47 | Helped |
| Add pixel-wise part locations (ablation) | ZoomNet · KITTI validation, occlusion level 2, Hard | AP3d (IoU=0.7): 5.56 -> 9.76 | Helped |
| Add adaptive zooming (ablation) | ZoomNet · KITTI validation, Hard | AP3d (IoU=0.7): 34.20 -> 43.63 | Helped |
| Add pixel-wise part locations (ablation) | ZoomNet · KITTI validation, Hard | AP3d (IoU=0.7): 34.51 -> 43.63 | Helped |
| Add a 3D fitting score (ablation) | ZoomNet · KITTI validation, Hard | AP3d (IoU=0.7): 40.88 -> 43.63 | Helped |
| Add both part locations and 3D fitting score (ablation) | ZoomNet · KITTI validation, Moderate | AP3d (IoU=0.7): 38.33 -> 50.47 | Helped |
| Replace image-level disparity with instance-wise disparity estimation | ZoomNet versus Pseudo-LiDAR · KITTI validation, Hard | AP3d (IoU=0.5): 61.20 -> 70.47 | Helped |
| Use ZoomNet instead of Stereo R-CNN | KITTI test, Moderate · KITTI test, Moderate | AP3d (IoU=0.7): 30.23 -> 38.64 | Helped |
Closest papers by meaning
- Omni3D: A Large Benchmark and Model for 3D Object Detection in the Wild (CVPR 2023 · similarity 0.89)
- Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection (CVPR 2023 · similarity 0.89)
- SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detection (CVPR 2024 · similarity 0.88)
- ImOV3D: Learning Open Vocabulary Point Clouds 3D Object Detection from Only 2D Images (NeurIPS 2024 · similarity 0.88)
- ViKIENet: Towards Efficient 3D Object Detection with Virtual Key Instance Enhanced Network (CVPR 2025 · similarity 0.87)
- Towards Generalizable Multi-Camera 3D Object Detection via Perspective Rendering (AAAI 2025 · 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.