Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Chang, Gyusam, Vu, Tuan-Anh, Alumootil, Vivek, Song, Harris, Pham, Deanna, Kim, Sangpil, Jawed, M. Khalid
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2508.14443
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866915452467281920
author Chang, Gyusam
Vu, Tuan-Anh
Alumootil, Vivek
Song, Harris
Pham, Deanna
Kim, Sangpil
Jawed, M. Khalid
author_facet Chang, Gyusam
Vu, Tuan-Anh
Alumootil, Vivek
Song, Harris
Pham, Deanna
Kim, Sangpil
Jawed, M. Khalid
contents While 3D Gaussian Splatting (3DGS) has rapidly advanced, its application in agriculture remains underexplored. Agricultural scenes present unique challenges for 3D reconstruction methods, particularly due to uneven illumination, occlusions, and a limited field of view. To address these limitations, we introduce \textbf{NIRPlant}, a novel multimodal dataset encompassing Near-Infrared (NIR) imagery, RGB imagery, textual metadata, Depth, and LiDAR data collected under varied indoor and outdoor lighting conditions. By integrating NIR data, our approach enhances robustness and provides crucial botanical insights that extend beyond the visible spectrum. Additionally, we leverage text-based metadata derived from vegetation indices, such as NDVI, NDWI, and the chlorophyll index, which significantly enriches the contextual understanding of complex agricultural environments. To fully exploit these modalities, we propose \textbf{NIRSplat}, an effective multimodal Gaussian splatting architecture employing a cross-attention mechanism combined with 3D point-based positional encoding, providing robust geometric priors. Comprehensive experiments demonstrate that \textbf{NIRSplat} outperforms existing landmark methods, including 3DGS, CoR-GS, and InstantSplat, highlighting its effectiveness in challenging agricultural scenarios. The code and dataset are publicly available at: https://github.com/StructuresComp/3D-Reconstruction-NIR
format Preprint
id arxiv_https___arxiv_org_abs_2508_14443
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting
Chang, Gyusam
Vu, Tuan-Anh
Alumootil, Vivek
Song, Harris
Pham, Deanna
Kim, Sangpil
Jawed, M. Khalid
Computer Vision and Pattern Recognition
While 3D Gaussian Splatting (3DGS) has rapidly advanced, its application in agriculture remains underexplored. Agricultural scenes present unique challenges for 3D reconstruction methods, particularly due to uneven illumination, occlusions, and a limited field of view. To address these limitations, we introduce \textbf{NIRPlant}, a novel multimodal dataset encompassing Near-Infrared (NIR) imagery, RGB imagery, textual metadata, Depth, and LiDAR data collected under varied indoor and outdoor lighting conditions. By integrating NIR data, our approach enhances robustness and provides crucial botanical insights that extend beyond the visible spectrum. Additionally, we leverage text-based metadata derived from vegetation indices, such as NDVI, NDWI, and the chlorophyll index, which significantly enriches the contextual understanding of complex agricultural environments. To fully exploit these modalities, we propose \textbf{NIRSplat}, an effective multimodal Gaussian splatting architecture employing a cross-attention mechanism combined with 3D point-based positional encoding, providing robust geometric priors. Comprehensive experiments demonstrate that \textbf{NIRSplat} outperforms existing landmark methods, including 3DGS, CoR-GS, and InstantSplat, highlighting its effectiveness in challenging agricultural scenarios. The code and dataset are publicly available at: https://github.com/StructuresComp/3D-Reconstruction-NIR
title Reconstruction Using the Invisible: Intuition from NIR and Metadata for Enhanced 3D Gaussian Splatting
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2508.14443