5 papers
ForestHG-Trace: Traceable Long-Horizon Ecological Reasoning over Large-Scale Forest Scenes
Zihang Cheng, Duanchu Wang, Cheng Li +3
Remote sensing question answering (RS-QA) often requires more than direct semantic prediction, especially in large-scale forest scenes where ecological analysis involves multi-step…
PointQ-Bench: Benchmarking Diagnostic and Interpretable Point Cloud Quality Assessment
Duanchu Wang, Cheng Li, Junjie Yang +6
Point cloud quality plays a critical role in 3D acquisition, reconstruction, rendering, and perception, yet existing point cloud quality assessment (PCQA) research remains largely…
VertiCue-Bench: Diagnosing Whether MLLMs Use Height Cues to Resolve 2D Ambiguity in Remote Sensing Natural Scenes
Jing Huang, Duanchu Wang, Junjie Yang +5
Multimodal Large Language Models (MLLMs) have recently shown promising progress in geospatial reasoning. However, existing remote sensing benchmarks remain largely 2D-centric, eval…
Advancing the Understanding of Fine-Grained 3D Forest Structures using Digital Cousins and Simulation-to-Reality: Methods and Datasets
Jing Liu, Duanchu Wang, Haoran Gong +3
Understanding and analyzing the spatial semantics and structure of forests is essential for accurate forest resource monitoring and ecosystem research. However, the lack of large-s…
CompetitorFormer: Competitor Transformer for 3D Instance Segmentation
Duanchu Wang, Jing Liu, Haoran Gong +2
Transformer-based methods have become the dominant approach for 3D instance segmentation. These methods predict instance masks via instance queries, ranking them by classification…