arXiv AI October 5, 2026 By Zhihao Zhan, Le Tao, Yifei Tian, Xin Liu, Jie Yuan

ForestQuery: Boundary-Aware and Spatially Anchored Query Learning for Unified Forest Point Cloud Segmentation

ForestQuery is a new framework for unified forest point cloud segmentation that incorporates boundary-aware and spatially anchored query learning. It explicitly models boundary uncertainty to improve instance query construction and uses learnable 3D anchors to encode forest vertical stratification for semantic queries. Experiments on public benchmarks and a real‑world dataset show consistent gains in both individual‑tree and semantic segmentation.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

arXiv Machine Learning

Jun 9

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

arXiv:2606. 08206v1 Announce Type: cross Abstract: We present SegmentAnyTreeV2, a sensor- and platform-agnostic framework for semantic and instance segmentation of forest point clouds.

By Maciej Wielgosz, Stefano Puliti, Rasmus Astrup

llms computer-vision benchmarks

arXiv Computer Vision

Sep 22

Toward a foundation model for forest point clouds

arXiv:2609.24787v1 Announce Type: new Abstract: Forest inventories increasingly rely on artificial intelligence (AI) models to derive forest attributes from large-scale 3D point clouds. Current model...

By Yuanwen Yue, Stefano Puliti, Damien Robert, Atakan Topalo\u{g}lu, Binbin Xiang, Maciej Wielgosz, Jan Dirk Wegner, Rasmus Astrup, Christian Rupprecht, Konrad Schindler

computer-vision benchmarks

arXiv Computer Vision

Aug 28

SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds

SelectAnyTree is a promptable instance segmentation model designed for 3D forest LiDAR point clouds, enabling users to delineate individual trees with a few clicks. The architecture comprises a sparse voxel scene encoder, a click‑to‑query prompt encoder, and a state‑space query decoder that produces tree masks in linear time, requiring only 19.4 M parameters. Across seven forest regions and an independent dataset, the model achieves a 79.9 % IoU for a single‑click target tree, outperforming existing promptable baselines and requiring the fewest clicks to reach accuracy targets.

By Trung Thanh Nguyen, Daniel Lusk, Kilian Gerberding, Janusch Vajna-Jehle, Tuan-Anh Vu, Duc Viet Le, Tu Vo, Phi Le Nguyen, Yasutomo Kawanishi, Takahiro Komamizu, Ichiro Ide, Julian Frey, Teja Kattenborn

computer-vision

arXiv AI

Jul 9

Self-Supervised Pretraining Improves Cross-Site and Cross-Scale Robustness of Point Cloud Leaf-Wood Segmentation

arXiv:2607. 06948v1 Announce Type: cross Abstract: The accuracy of existing leaf-wood segmentation methods for tree point clouds varies across forest types and sites.

By Heeju Mun, Tackang Yang, Yunsoo Nam, Changhyun Choi

computer-vision fine-tuning benchmarks

arXiv Computer Vision

Sep 15

Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

arXiv:2603.25165v3 Announce Type: replace Abstract: Recent advances in self-supervised learning (SSL) for point clouds have substantially improved 3D scene understanding without human annotations. Ex...

By Bin Yang, Mohamed Abdelsamad, Miao Zhang, Alexandru Paul Condurache

computer-vision fine-tuning

Hugging Face Trending Papers

Aug 3

SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models

Vision-language models (VLMs) achieve strong semantic understanding but remain unreliable in metric spatial reasoning, particularly when queries require comparing multiple instances of the same object category. We study this problem through the Closest-Instance Distance Query (CIDQ), where a model must identify the nearest visible candidate to a unique reference object and estimate their gravity-aligned floor-plane distance.

llms fine-tuning multimodal benchmarks

One email a morning, machine-written

Related stories

SegmentAnyTreeV2: Scaling Transformer-Based Tree Instance Segmentation Across Sensors, Platforms, and Forests

Toward a foundation model for forest point clouds

SelectAnyTree: A Promptable Instance Segmentation Model for 3D Forest LiDAR Point Clouds

Self-Supervised Pretraining Improves Cross-Site and Cross-Scale Robustness of Point Cloud Leaf-Wood Segmentation

Towards Foundation Models for 3D Scene Understanding: Instance-Aware Self-Supervised Learning for Point Clouds

SpatialQuery: Benchmarking Geometry-Grounded Multi-Instance Spatial Reasoning in Vision-Language Models