# ZoomNet: Part-Aware Adaptive Zooming Neural Network for 3D Object Detection

arXiv: https://arxiv.org/abs/2003.00529 · HTML: https://mlsanity.com/paper/2003.00529/

## Key facts

- Cited by 25 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Mar 2020.

## Built on by (most cited first, 25 of 25)

- [3D Object Detection for Autonomous Driving: A Comprehensive Survey](https://mlsanity.com/paper/2206.09474/) (2022)
- [Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe](https://mlsanity.com/paper/2209.05324/) (2022)
- [SPG: Unsupervised Domain Adaptation for 3D Object Detection via Semantic Point Generation](https://mlsanity.com/paper/2108.06709/) (2021)
- [LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector](https://mlsanity.com/paper/2108.08258/) (2021)
- [Learning Auxiliary Monocular Contexts Helps Monocular 3D Object Detection](https://mlsanity.com/paper/2112.04628/) (2021)
- [3D Object Detection from Images for Autonomous Driving: A Survey](https://mlsanity.com/paper/2202.02980/) (2022)
- [Multimodal Fusion and Vision-Language Models: A Survey for Robot Vision](https://mlsanity.com/paper/2504.02477/) (2025)
- [Monocular 3D Object Detection with Depth from Motion](https://mlsanity.com/paper/2207.12988/) (2022)
- [YOLOStereo3D: A Step Back to 2D for Efficient Stereo 3D Detection](https://mlsanity.com/paper/2103.09422/) (2021)
- [PLUMENet: Efficient 3D Object Detection from Stereo Images](https://mlsanity.com/paper/2101.06594/) (2021)
- [AccidentGPT: Accident Analysis and Prevention from V2X Environmental Perception with Multi-modal Large Model](https://mlsanity.com/paper/2312.13156/) (2023)
- [MonoCInIS: Camera Independent Monocular 3D Object Detection using Instance Segmentation](https://mlsanity.com/paper/2110.00464/) (2021)
- [Stereo CenterNet based 3D Object Detection for Autonomous Driving](https://mlsanity.com/paper/2103.11071/) (2021)
- [DSGN++: Exploiting Visual-Spatial Relation for Stereo-based 3D Detectors](https://mlsanity.com/paper/2204.03039/) (2022)
- [ESGN: Efficient Stereo Geometry Network for Fast 3D Object Detection](https://mlsanity.com/paper/2111.14055/) (2021)
- [StereoDistill: Pick the Cream from LiDAR for Distilling Stereo-based 3D Object Detection](https://mlsanity.com/paper/2301.01615/) (2023)
- [Stereo Neural Vernier Caliper](https://mlsanity.com/paper/2203.11018/) (2022)
- [Transformer-based stereo-aware 3D object detection from binocular images](https://mlsanity.com/paper/2304.11906/) (2023)
- [Joint stereo 3D object detection and implicit surface reconstruction](https://mlsanity.com/paper/2111.12924/) (2021)
- [SoK: Vehicle Orientation Representations for Deep Rotation Estimation](https://mlsanity.com/paper/2112.04421/) (2021)
- [Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?](https://mlsanity.com/paper/2206.13858/) (2022)
- [Towards Fair and Comprehensive Comparisons for Image-Based 3D Object Detection](https://mlsanity.com/paper/2310.05447/) (2023)
- [Real-time Stereo-based 3D Object Detection for Streaming Perception](https://mlsanity.com/paper/2410.12394/) (2024)
- [Shape Prior Non-Uniform Sampling Guided Real-time Stereo 3D Object Detection](https://mlsanity.com/paper/2106.10013/) (2021)
- [Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving](https://mlsanity.com/paper/2403.02037/) (2024)

## Abstract (arXiv)

3D object detection is an essential task in autonomous driving and robotics. Though great progress has been made, challenges remain in estimating 3D pose for distant and occluded objects. In this paper, we present a novel framework named ZoomNet for stereo imagery-based 3D detection. The pipeline of ZoomNet begins with an ordinary 2D object detection model which is used to obtain pairs of left-right bounding boxes. To further exploit the abundant texture cues in RGB images for more accurate disparity estimation, we introduce a conceptually straight-forward module -- adaptive zooming, which simultaneously resizes 2D instance bounding boxes to a unified resolution and adjusts the camera intrinsic parameters accordingly. In this way, we are able to estimate higher-quality disparity maps from the resized box images then construct dense point clouds for both nearby and distant objects. Moreover, we introduce to learn part locations as complementary features to improve the resistance against occlusion and put forward the 3D fitting score to better estimate the 3D detection quality. Extensive experiments on the popular KITTI 3D detection dataset indicate ZoomNet surpasses all previous state-of-the-art methods by large margins (improved by 9.4% on APbv (IoU=0.7) over pseudo-LiDAR). Ablation study also demonstrates that our adaptive zooming strategy brings an improvement of over 10% on AP3d (IoU=0.7). In addition, since the official KITTI benchmark lacks fine-grained annotations like pixel-wise part locations, we also present our KFG dataset by augmenting KITTI with detailed instance-wise annotations including pixel-wise part location, pixel-wise disparity, etc.. Both the KFG dataset and our codes will be publicly available at https://github.com/detectRecog/ZoomNet.