# CountingFruit: Language-Guided 3D Fruit Counting with Semantic Gaussian Splatting

arXiv: https://arxiv.org/abs/2506.01109 · HTML: https://mlsanity.com/paper/2506.01109/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 25 references that are in the map.
- First posted on arXiv 1 Jun 2025.

## Builds on (most cited first, 11 of 11)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [You Only Look Once: Unified, Real-Time Object Detection](https://mlsanity.com/paper/1506.02640/) (2015)
- [LangSplat: 3D Language Gaussian Splatting](https://mlsanity.com/paper/2312.16084/) (2023)
- [Taming 3DGS: High-Quality Radiance Fields with Limited Resources](https://mlsanity.com/paper/2406.15643/) (2024)
- [AdR-Gaussian: Accelerating Gaussian Splatting with Adaptive Radius](https://mlsanity.com/paper/2409.08669/) (2024)
- [FruitNeRF: A Unified Neural Radiance Field based Fruit Counting Framework](https://mlsanity.com/paper/2408.06190/) (2024)
- [Robust Fruit Counting: Combining Deep Learning, Tracking, and Structure from Motion](https://mlsanity.com/paper/1804.00307/) (2018)
- [FruitNeRF++: A Generalized Multi-Fruit Counting Method Utilizing Contrastive Learning and Neural Radiance Fields](https://mlsanity.com/paper/2505.19863/) (2025)
- [High-Precision Fruit Localization Using Active Laser-Camera Scanning: Robust Laser Line Extraction for 2D-3D Transformation](https://mlsanity.com/paper/2311.08674/) (2023)

## Abstract (arXiv)

Accurate 3D fruit counting in orchards is challenging due to heavy occlusion, semantic ambiguity between fruits and surrounding structures, and the high computational cost of volumetric reconstruction. Existing pipelines often rely on multi-view 2D segmentation and dense volumetric sampling, which lead to accumulated fusion errors and slow inference. We introduce FruitLangGS, a language-guided 3D fruit counting framework that reconstructs orchard-scale scenes using an adaptive-density Gaussian Splatting pipeline with radius-aware pruning and tile-based rasterization, enabling scalable 3D representation. During inference, compressed CLIP-aligned semantic vectors embedded in each Gaussian are filtered via a dual-threshold cosine similarity mechanism, retrieving Gaussians relevant to target prompts while suppressing common distractors (e.g., foliage), without requiring retraining or image-space masks. The selected Gaussians are then sampled into dense point clouds and clustered geometrically to estimate fruit instances, remaining robust under severe occlusion and viewpoint variation. Experiments on nine different orchard-scale datasets demonstrate that FruitLangGS consistently outperforms existing pipelines in instance counting recall, avoiding multi-view segmentation fusion errors and achieving up to 99.7% recall on Pfuji-Size_Orch2018 orchard dataset. Ablation studies further confirm that language-conditioned semantic embedding and dual-threshold prompt filtering are essential for suppressing distractors and improving counting accuracy under heavy occlusion. Beyond fruit counting, the same framework enables prompt-driven 3D semantic retrieval without retraining, highlighting the potential of language-guided 3D perception for scalable agricultural scene understanding.