# Transformer-Based Spatio-Temporal Association of Apple Fruitlets

arXiv: https://arxiv.org/abs/2503.03200 · HTML: https://mlsanity.com/paper/2503.03200/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 43 references that are in the map.
- First posted on arXiv 5 Mar 2025.

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

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Mask R-CNN](https://mlsanity.com/paper/1703.06870/) (2017)
- [Optuna: A Next-generation Hyperparameter Optimization Framework](https://mlsanity.com/paper/1907.10902/) (2019)
- [4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks](https://mlsanity.com/paper/1904.08755/) (2019)
- [LoFTR: Detector-Free Local Feature Matching with Transformers](https://mlsanity.com/paper/2104.00680/) (2021)
- [LightGlue: Local Feature Matching at Light Speed](https://mlsanity.com/paper/2306.13643/) (2023)
- [RAFT-Stereo: Multilevel Recurrent Field Transforms for Stereo Matching](https://mlsanity.com/paper/2109.07547/) (2021)
- [A Robust Illumination-Invariant Camera System for Agricultural Applications](https://mlsanity.com/paper/2101.02190/) (2021)
- [Bumblebee: A Path Towards Fully Autonomous Robotic Vine Pruning](https://mlsanity.com/paper/2112.00291/) (2021)
- [4D Crop Monitoring: Spatio-Temporal Reconstruction for Agriculture](https://mlsanity.com/paper/1610.02482/) (2016)
- [Vision Transformers For Weeds and Crops Classification Of High Resolution UAV Images](https://mlsanity.com/paper/2109.02716/) (2021)
- [3D Reconstruction-Based Seed Counting of Sorghum Panicles for Agricultural Inspection](https://mlsanity.com/paper/2211.07748/) (2022)
- [Statistical shape representations for temporal registration of plant components in 3D](https://mlsanity.com/paper/2209.11526/) (2022)
- [Autonomous Apple Fruitlet Sizing and Growth Rate Tracking using Computer Vision](https://mlsanity.com/paper/2212.01506/) (2022)
- [Autonomous Apple Fruitlet Sizing with Next Best View Planning](https://mlsanity.com/paper/2309.13669/) (2023)
- [MOT-DETR: 3D Single Shot Detection and Tracking with Transformers to build 3D representations for Agro-Food Robots](https://mlsanity.com/paper/2311.15674/) (2023)
- [Unsupervised Pre-Training for 3D Leaf Instance Segmentation](https://mlsanity.com/paper/2401.08720/) (2024)

## Built on by (most cited first, 1 of 1)

- [GrowFields: Compositional 4D Neural Fields for Topology-Changing Plant Growth](https://mlsanity.com/paper/2607.03330/) (2026)

## Abstract (arXiv)

In this paper, we present a transformer-based method to spatio-temporally associate apple fruitlets in stereo-images collected on different days and from different camera poses. State-of-the-art association methods in agriculture are dedicated towards matching larger crops using either high-resolution point clouds or temporally stable features, which are both difficult to obtain for smaller fruit in the field. To address these challenges, we propose a transformer-based architecture that encodes the shape and position of each fruitlet, and propagates and refines these features through a series of transformer encoder layers with alternating self and cross-attention. We demonstrate that our method is able to achieve an F1-score of 92.4% on data collected in a commercial apple orchard and outperforms all baselines and ablations.