# Simultaneous multi-view instance detection with learned geometric soft-constraints

arXiv: https://arxiv.org/abs/1907.10892 · HTML: https://mlsanity.com/paper/1907.10892/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 25 Jul 2019.

## Built on by (most cited first, 11 of 11)

- [SAIL-VOS 3D: A Synthetic Dataset and Baselines for Object Detection and 3D Mesh Reconstruction from Video Data](https://mlsanity.com/paper/2105.08612/) (2021)
- [DOLPHINS: Dataset for Collaborative Perception enabled Harmonious and Interconnected Self-driving](https://mlsanity.com/paper/2207.07609/) (2022)
- [Visual and Object Geo-localization: A Comprehensive Survey](https://mlsanity.com/paper/2112.15202/) (2021)
- [Object Tracking and Geo-localization from Street Images](https://mlsanity.com/paper/2107.06257/) (2021)
- [Maps from Motion (MfM): Generating 2D Semantic Maps from Sparse Multi-view Images](https://mlsanity.com/paper/2411.12620/) (2024)
- [TopView: Vectorising road users in a bird's eye view from uncalibrated street-level imagery with deep learning](https://mlsanity.com/paper/2412.16229/) (2024)
- [Improving Cross-view Object Geo-localization: A Dual Attention Approach with Cross-view Interaction and Multi-Scale Spatial Features](https://mlsanity.com/paper/2510.27139/) (2025)
- [SVII-3D: Advancing Roadside Infrastructure Inventory with Decimeter-level 3D Localization and Comprehension from Sparse Street Imagery](https://mlsanity.com/paper/2601.10535/) (2026)
- [Framework and Multi-modal Dataset for Roadwork Zone Detection and Geo-localization](https://mlsanity.com/paper/2607.04330/) (2026)
- [STRIDE: Street View-based Environmental Feature Detection and Pedestrian Collision Prediction](https://mlsanity.com/paper/2308.13183/) (2023)
- [WHU-Infra3D: A Full-stack Multi-modal Dataset and Benchmark for 3D Roadside Infrastructure Inventory](https://mlsanity.com/paper/2606.09882/) (2026)

## Abstract (arXiv)

We propose to jointly learn multi-view geometry and warping between views of the same object instances for robust cross-view object detection. What makes multi-view object instance detection difficult are strong changes in viewpoint, lighting conditions, high similarity of neighbouring objects, and strong variability in scale. By turning object detection and instance re-identification in different views into a joint learning task, we are able to incorporate both image appearance and geometric soft constraints into a single, multi-view detection process that is learnable end-to-end. We validate our method on a new, large data set of street-level panoramas of urban objects and show superior performance compared to various baselines. Our contribution is threefold: a large-scale, publicly available data set for multi-view instance detection and re-identification; an annotation tool custom-tailored for multi-view instance detection; and a novel, holistic multi-view instance detection and re-identification method that jointly models geometry and appearance across views.