mlsanityData to 19 Oct 2026

Efficient View Planning Guided by Previous-Session Reconstruction for Repeated Plant Monitoring

arXiv 2510.07028 ↗First posted 8 Oct 2025cs.ROcited by 0

On the map: 3D reconstruction and neural rendering → Plant and agricultural 3D reconstruction

Abstract (arXiv)

Repeated plant monitoring is essential for tracking crop growth, and 3D reconstruction enables consistent comparison across monitoring sessions. However, rebuilding a 3D model from scratch in every session is costly and overlooks informative geometry already observed previously. We propose efficient view planning guided by a previous-session reconstruction, which reuses a 3D model from the previous session to improve active perception in the current session. Based on this previous-session reconstruction, our method replaces iterative next-best-view planning with one-shot view planning that selects an informative set of views and computes the globally shortest execution path connecting them. Experiments on real multi-session datasets, including public single-plant scans and a newly collected greenhouse crop-row dataset, show that our method achieves comparable or higher surface coverage with fewer executed views and shorter robot paths than iterative and one-shot baselines.

Key facts. No citing papers in the map yet (data through 19 Oct 2026). Placed in Plant and agricultural 3D reconstruction, one of 15 directions in 3D reconstruction and neural rendering. Builds on 24 of its 47 references that are in the map. First posted on arXiv 8 Oct 2025.

Builds on

24 of 47 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024SSL-NBV: A Self-Supervised-Learning-Based Next-Best-View algorithm for Efficient 3D Plant Reconstruction by a Robot2 Oct

Other references · 23

  1. 2014Adam: A Method for Stochastic Optimizationcited by 38,210
  2. 2018Open3D: A Modern Library for 3D Data Processingcited by 737
  3. 2023Nerfstudio: A Modular Framework for Neural Radiance Field Developmentcited by 631
  4. 2018FlowNet3D: Learning Scene Flow in 3D Point Cloudscited by 243
  5. 2019HPLFlowNet: Hierarchical Permutohedral Lattice FlowNet for Scene Flow Estimation on Large-scale Point Cloudscited by 110
  6. 2022A Survey of Non-Rigid 3D Registrationcited by 61
  7. 2019Supervised Learning of the Next-Best-View for 3D Object Reconstructioncited by 29
  8. 2020PATHoBot: A Robot for Glasshouse Crop Phenotyping and Interventioncited by 19
  9. 2020Viewpoint Planning for Fruit Size and Position Estimationcited by 13
  10. 2022NBV-SC: Next Best View Planning based on Shape Completion for Fruit Mapping and Reconstructioncited by 13
  11. 2022Attention-driven Next-best-view Planning for Efficient Reconstruction of Plants and Targeted Plant Partscited by 12
  12. 2023How Many Views Are Needed to Reconstruct an Unknown Object Using NeRF?cited by 11
11 more
  1. 20164D Crop Monitoring: Spatio-Temporal Reconstruction for Agriculturecited by 10
  2. 2023Graph-based View Motion Planning for Fruit Detectioncited by 7
  3. 2023Integrating One-Shot View Planning with a Single Next-Best View via Long-Tail Multiview Samplingcited by 6
  4. 2023Active Implicit Reconstruction Using One-Shot View Planningcited by 6
  5. 2023Gradient-based Local Next-best-view Planning for Improved Perception of Targeted Plant Nodescited by 6
  6. 2024Exploiting Priors from 3D Diffusion Models for RGB-Based One-Shot View Planningcited by 5
  7. 2025GO-VMP: Global Optimization for View Motion Planning in Fruit Mappingcited by 5
  8. 2022Statistical shape representations for temporal registration of plant components in 3Dcited by 3
  9. 2025DM-OSVP++: One-Shot View Planning Using 3D Diffusion Models for Active RGB-Based Object Reconstructioncited by 3
  10. 2024Enhancing Agricultural Environment Perception via Active Vision and Zero-Shot Learningcited by 2
  11. 2025Transformer-Based Spatio-Temporal Association of Apple Fruitletscited by 2

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026Receding-Horizon Next-Best-View Planner for Autonomous Leaf Surface Reconstruction
  2. 2025BOSfM: A View Planning Framework for Optimal 3D Reconstruction of Agricultural Scenes
  3. 2026UAV3DCrop: Benchmarking 3D Reconstruction in Repeated Multi-Angle UAV Crop Surveys
  4. 2025AgriChrono: A Multi-modal Dataset Capturing Crop Growth and Lighting Variability with a Field Robot
  5. 2026The Turning Point of 3D Plant Phenotyping: 3D Foundation Models Enable Minute-to-Second Cross-Crop Reconstruction and Beyond
  6. 2024CropCraft: Complete Structural Characterization of Crop Plants From Images
  7. 2026Grow with the Flow: 4D Reconstruction of Growing Plants with Gaussian Flow Fields
  8. 2025Enhanced View Planning for Robotic Harvesting: Tackling Occlusions with Imitation Learning