Progressive Per-Branch Depth Optimization for DEFOM-Stereo and SAM3 Joint Analysis in UAV Forestry Applications

• URL: http://arxiv.org/abs/2602.20539v1
• Date: Tue, 24 Feb 2026 04:37:18 GMT
• Title: Progressive Per-Branch Depth Optimization for DEFOM-Stereo and SAM3 Joint Analysis in UAV Forestry Applications
• Abstract summary: Per-branch 3D reconstruction is a prerequisite for autonomous UAV-based tree pruning.<n>This paper introduces a progressive pipeline integrating DEFOM-Stereo foundation-model disparity estimation.<n>The proposed pipeline reduces the average per-branch depth standard deviation by 82% while retaining edge fidelity.
• Score: 5.266753902938501
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Accurate per-branch 3D reconstruction is a prerequisite for autonomous UAV-based tree pruning; however, dense disparity maps from modern stereo matchers often remain too noisy for individual branch analysis in complex forest canopies. This paper introduces a progressive pipeline integrating DEFOM-Stereo foundation-model disparity estimation, SAM3 instance segmentation, and multi-stage depth optimization to deliver robust per-branch point clouds. Starting from a naive baseline, we systematically identify and resolve three error families through successive refinements. Mask boundary contamination is first addressed through morphological erosion and subsequently refined via a skeleton-preserving variant to safeguard thin-branch topology. Segmentation inaccuracy is then mitigated using LAB-space Mahalanobis color validation coupled with cross-branch overlap arbitration. Finally, depth noise - the most persistent error source - is initially reduced by outlier removal and median filtering, before being superseded by a robust five-stage scheme comprising MAD global detection, spatial density consensus, local MAD filtering, RGB-guided filtering, and adaptive bilateral filtering. Evaluated on 1920x1080 stereo imagery of Radiata pine (Pinus radiata) acquired with a ZED Mini camera (63 mm baseline) from a UAV in Canterbury, New Zealand, the proposed pipeline reduces the average per-branch depth standard deviation by 82% while retaining edge fidelity. The result is geometrically coherent 3D point clouds suitable for autonomous pruning tool positioning. All code and processed data are publicly released to facilitate further UAV forestry research.

Related papers

• Learning Spherical Occupancy Profiles for Multi-View 3D Reconstruction and Generation [25.01274737585538]
  We train a discriminative per-ray decoder that injects global view-averaged and ray-specific image evidence into a FiLM-conditioned profile head.<n>We analyze the morphology of predicted profiles and show that ray-wise occupancy profiles offer a compact, learned, and uncertainty-aware interface between multi-view reconstruction and generative priors.
  arXiv  Detail & Related papers  (2026-08-24T12:56:39Z)
• LinStereo: Linear-Complexity Global Attention for Multi-Scale Iterative Stereo Matching [4.952844628691303]
  LinStereo is a Position-Aware Linear Attention (PALA) module that replaces local recurrence with global aggregation at linear cost.<n>It achieves state-of-the-art-level accuracy on standard benchmarks and strong cross-domain generalization.<n>It achieves the best overall accuracy with consistent gains 28% lower AbsRel on TartanAir-UW, 26% on SQUID, a real-world underwater dataset.
  arXiv  Detail & Related papers  (2026-06-24T05:58:03Z)
• CMDS-AD: Cross-Modal Dual-Stream Decoupling for Few-Shot Anomaly Detection [22.190054508477704]
  Few-shot anomaly detection remains challenging due to limited training data.<n>We present CMDS-AD, a Cross-Modal Dual-Stream Anomaly Detection framework.<n> CMDS-AD achieves absolute performance gains of 5.7% (I-AUROC) and 2.0% (AUPRO) on MVTec 3D-AD, alongside 7.7% and 5.6% improvements on EyeCandies.
  arXiv  Detail & Related papers  (2026-06-18T14:36:02Z)
• Closed-Form Spectral Regularization for Multi-Task Model Merging [96.82449201305234]
  Model merging combines several independently fine-tuned experts into a single multi-task model without any training data.<n>State-of-the-art merging methods formulate merging as a layer-wise interference problem.<n>We propose SWUDI, a closed-form method that combines a soft exponential filter, which matches the gradient-flow trajectory of iterative descent.
  arXiv  Detail & Related papers  (2026-06-05T14:00:47Z)
• Low-Cost Stereo Vision for Robust 3D Positioning of Thin Radiata Pine Branches in Autonomous Drone Pruning [5.266753902938501]
  Existing autonomous pruning platforms typically rely on expensive sensors such as LiDAR.<n>This paper investigates whether a single low-cost stereo camera mounted on a drone can provide sufficiently accurate branch detection.
  arXiv  Detail & Related papers  (2026-05-06T10:01:25Z)
• Positioning radiata pine branches requiring pruning by drone stereo vision [5.266753902938501]
  This paper presents a stereo-vision-based system mounted on a drone for detecting and localising radiata pine branches to support autonomous pruning.<n>For segmentation, YOLOv8, YOLOv9, and Mask R-CNN variants are compared on a custom dataset of 71 stereo image pairs captured with a ZED Mini camera.<n>For depth estimation, both a traditional method (SGBM with WLS filtering) and deep-learning-based methods are evaluated.<n>A centroid-based triangulation algorithm with MAD outlier rejection is proposed to compute branch distance from the segmentation mask and disparity map.
  arXiv  Detail & Related papers  (2026-04-12T10:10:19Z)
• Unifying UAV Cross-View Geo-Localization via 3D Geometric Perception [51.687842983240564]
  Cross-view geo-localization for Unmanned Aerial Vehicles (UAVs) remains challenging due to the severe geometric discrepancy between oblique UAV imagery and satellite maps.<n>We propose a geometry-aware UAV geo-localization framework that explicitly models the 3D scene geometry to unify coarse place recognition and fine-grained pose estimation.<n>Our method significantly outperforms state-of-the-art baselines, achieving robust meter-level localization accuracy and improved generalization in complex urban environments.
  arXiv  Detail & Related papers  (2026-04-02T08:08:41Z)
• Structure-Informed Estimation for Pilot-Limited MIMO Channels via Tensor Decomposition [51.56484100374058]
  This paper formulates pilot-limited channel estimation as low-rank tensor completion from sparse observations.<n>Experiments on synthetic channels demonstrate 10-20,dB normalized mean-square error (NMSE) improvement over least-squares (LS)<n> evaluations on DeepMIMO ray-tracing channels show 24-44% additional NMSE reduction over pure tensor-based methods.
  arXiv  Detail & Related papers  (2026-02-03T23:38:05Z)
• Cross-Modal Alignment and Fusion for RGB-D Transmission-Line Defect Detection [11.637942429146172]
  This paper proposes CMAFNet, a Cross-Modal Alignment and Fusion Network that integrates RGB appearance and depth geometry through a principled-then-fuse paradigm.<n> CMAFNet consists of a Semantic Recomposition Module that performs dictionary-based feature purification.<n>A lightweight variant reaches 24.8% mAP50 at 228 FPS with only 4.9M parameters, surpassing all YOLO-based detectors.
  arXiv  Detail & Related papers  (2026-02-02T06:11:33Z)
• D3R-Net: Dual-Domain Denoising Reconstruction Network for Robust Industrial Anomaly Detection [0.0]
  Unsupervised anomaly detection (UAD) is a key ingredient of automated visual inspection in modern manufacturing.<n>We introduce D3R-Net, a Dual-Domain Denoising Reconstruction framework that couples a self-supervised 'healing' task with frequency-aware regularization.<n>In addition to the spatial mean squared error, we employ a Fast Fourier Transform (FFT) magnitude loss that encourages consistency in the frequency domain.
  arXiv  Detail & Related papers  (2026-01-27T23:21:59Z)
• Unified Unsupervised Anomaly Detection via Matching Cost Filtering [113.43366521994396]
  Unsupervised anomaly detection (UAD) aims to identify image- and pixel-level anomalies using only normal training data.<n>We present Unified Cost Filtering (UCF), a generic post-hoc refinement framework for refining anomaly cost volume of any UAD model.
  arXiv  Detail & Related papers  (2025-10-03T03:28:18Z)
• A Novel Preprocessing Unit for Effective Deep Learning based Classification and Grading of Diabetic Retinopathy [0.0]
  This research performs detection of diabetic retinopathy at an early stage through the proposed framework.<n>The framework includes three stages: preprocessing, segmentation, feature extraction, and classification.<n>The effectiveness of the proposed method is assessed using two distinct datasets: IDRiD and MESSIDOR.
  arXiv  Detail & Related papers  (2025-09-29T09:11:04Z)
• Data-Driven Reconstruction of Significant Wave Heights from Sparse Observations [3.356199201143573]
  We introduce AUWave, a hybrid deep learning framework that fuses a station-wise sequence encoder (MLP) with a multi-scale U-Net.<n>We show that AUWave consistently outperforms a representative baseline in data-richer configurations.<n>The architecture's multi-scale and attention components translate into accuracy gains when minimal but non-trivial spatial anchoring is available.
  arXiv  Detail & Related papers  (2025-09-21T14:12:28Z)
• Taming Anomalies with Down-Up Sampling Networks: Group Center Preserving Reconstruction for 3D Anomaly Detection [59.822737536103155]
  A Down-Up Sampling Network (DUS-Net) is proposed to reconstruct high-precision point clouds for 3D anomaly detection by preserving the group center geometric structure.<n>The proposed method achieves state-of-the-art (SOTA) performance with an Object-level AUROC of 79.9% and 79.5%, and a Point-level AUROC of 71.2% and 84.7% on the Real3D-AD and Anomaly-ShapeNet datasets.
  arXiv  Detail & Related papers  (2025-07-05T05:05:36Z)
• CostFilter-AD: Enhancing Anomaly Detection through Matching Cost Filtering [64.24198178156627]
  Unsupervised anomaly detection (UAD) seeks to localize the anomaly mask of an input image with respect to normal samples.<n>We introduce the concept of cost filtering, borrowed from classical matching tasks, into the UAD problem.<n>We propose a cost volume filtering network, guided by the input observation as an attention query across multiple feature layers.
  arXiv  Detail & Related papers  (2025-05-02T14:52:34Z)
• An ocean front detection and tracking algorithm [4.0604303269549185]
  This paper proposes the Bayesian Front Detection and Tracking framework with Metric Space Analysis.<n>BFDTMSA reduces over-detection by $73%$ compared to histogram-based methods.<n>The open-source release bridges a critical gap in reproducible oceanographic research.
  arXiv  Detail & Related papers  (2025-02-21T07:00:09Z)
• Orthogonal Matrix Retrieval with Spatial Consensus for 3D Unknown-View Tomography [58.60249163402822]
  Unknown-view tomography (UVT) reconstructs a 3D density map from its 2D projections at unknown, random orientations. The proposed OMR is more robust and performs significantly better than the previous state-of-the-art OMR approach.
  arXiv  Detail & Related papers  (2022-07-06T21:40:59Z)
• The KFIoU Loss for Rotated Object Detection [115.334070064346]
  In this paper, we argue that one effective alternative is to devise an approximate loss who can achieve trend-level alignment with SkewIoU loss. Specifically, we model the objects as Gaussian distribution and adopt Kalman filter to inherently mimic the mechanism of SkewIoU. The resulting new loss called KFIoU is easier to implement and works better compared with exact SkewIoU.
  arXiv  Detail & Related papers  (2022-01-29T10:54:57Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.