# MVAT: Multi-View Aware Teacher for Weakly Supervised 3D Object Detection

arXiv: https://arxiv.org/abs/2509.07507 · HTML: https://mlsanity.com/paper/2509.07507/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 17 of its 27 references that are in the map.
- First posted on arXiv 9 Sep 2025.

## Builds on (most cited first, 17 of 17)

- [nuScenes: A multimodal dataset for autonomous driving](https://mlsanity.com/paper/1903.11027/) (2019)
- [SAM 2: Segment Anything in Images and Videos](https://mlsanity.com/paper/2408.00714/) (2024)
- [Center-based 3D Object Detection and Tracking](https://mlsanity.com/paper/2006.11275/) (2020)
- [PV-RCNN: Point-Voxel Feature Set Abstraction for 3D Object Detection](https://mlsanity.com/paper/1912.13192/) (2019)
- [Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detection](https://mlsanity.com/paper/2303.11926/) (2023)
- [Time Will Tell: New Outlooks and A Baseline for Temporal Multi-View 3D Object Detection](https://mlsanity.com/paper/2210.02443/) (2022)
- [Extreme clicking for efficient object annotation](https://mlsanity.com/paper/1708.02750/) (2017)
- [Temporal Enhanced Training of Multi-view 3D Object Detector via Historical Object Prediction](https://mlsanity.com/paper/2304.00967/) (2023)
- [FGR: Frustum-Aware Geometric Reasoning for Weakly Supervised 3D Vehicle Detection](https://mlsanity.com/paper/2105.07647/) (2021)
- [Semi-supervised 3D Object Detection via Temporal Graph Neural Networks](https://mlsanity.com/paper/2202.00182/) (2022)
- [Multimodal Transformer for Automatic 3D Annotation and Object Detection](https://mlsanity.com/paper/2207.09805/) (2022)
- [MAP-Gen: An Automated 3D-Box Annotation Flow with Multimodal Attention Point Generator](https://mlsanity.com/paper/2203.15700/) (2022)
- [Weakly Supervised 3D Object Detection via Multi-Level Visual Guidance](https://mlsanity.com/paper/2312.07530/) (2023)
- [General Geometry-aware Weakly Supervised 3D Object Detection](https://mlsanity.com/paper/2407.13748/) (2024)
- [Context-Aware Transformer for 3D Point Cloud Automatic Annotation](https://mlsanity.com/paper/2303.14893/) (2023)
- [Point-DETR3D: Leveraging Imagery Data with Spatial Point Prior for Weakly Semi-supervised 3D Object Detection](https://mlsanity.com/paper/2403.15317/) (2024)
- [ALPI: Auto-Labeller with Proxy Injection for 3D Object Detection using 2D Labels Only](https://mlsanity.com/paper/2407.17197/) (2024)

## Abstract (arXiv)

Annotating 3D data remains a costly bottleneck for 3D object detection, motivating the development of weakly supervised annotation methods that rely on more accessible 2D box annotations. However, relying solely on 2D boxes introduces projection ambiguities since a single 2D box can correspond to multiple valid 3D poses. Furthermore, partial object visibility under a single viewpoint setting makes accurate 3D box estimation difficult. We propose MVAT, a novel framework that leverages temporal multi-view present in sequential data to address these challenges. Our approach aggregates object-centric point clouds across time to build 3D object representations as dense and complete as possible. A Teacher-Student distillation paradigm is employed: The Teacher network learns from single viewpoints but targets are derived from temporally aggregated static objects. Then the Teacher generates high quality pseudo-labels that the Student learns to predict from a single viewpoint for both static and moving objects. The whole framework incorporates a multi-view 2D projection loss to enforce consistency between predicted 3D boxes and all available 2D annotations. Experiments on the nuScenes and Waymo Open datasets demonstrate that MVAT achieves state-of-the-art performance for weakly supervised 3D object detection, significantly narrowing the gap with fully supervised methods without requiring any 3D box annotations. % footnoteCode available upon acceptance Our code is available in our public repository (hrefhttps://github.com/CEA-LIST/MVATcode).