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

Abstract

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.

Plant phenotyping relevance

果実個数という植物器官形質を推定する3D画像解析手法を開発し、複数データセットで性能検証しているため、植物フェノタイピング手法が研究の中心である。

Code and data availability

The supplied blocks describe the FruitLangGS method and experiments on third-party orchard datasets (FruitNeRF benchmark, PFuji-Size, and CVPRW orchard sequences), but contain no authors' public code, data, model, or supplement links, and no availability statements. No allowed URLs are provided, so no paper-specific,公开

No evidence-backed public reproduction asset is currently recorded.