Eastern Institute of Technology, Ningbo

On five-direction UAV oblique surveys at roughly 1 cm nadir ground sampling distance, MV-PVMapper couples the frozen vision foundation model SAM 3 with photogrammetric geometry to output georeferenced polygons for individual modules without task-specific annotation or weight updates. Across three operational rooftop PV plants holding 7,711 reference modules, two feedback rounds match 7,710 with no false positives at an IoU threshold of 0.5; macro-averaged AJI reaches 97.55%, against 60.73% for an orthomosaic segmentation baseline and 41.24% for a multi-view pixel-voting baseline.

On five-direction UAV oblique surveys at roughly 1 cm nadir ground sampling distance, MV-PVMapper couples the frozen vision foundation model SAM 3 with photogrammetric geometry to output georeferenced polygons for individual modules without task-specific annotation or weight updates. Across three operational rooftop PV plants holding 7,711 reference modules, two feedback rounds match 7,710 with no false positives at an IoU threshold of 0.5; macro-averaged AJI reaches 97.55%, against 60.73% for an orthomosaic segmentation baseline and 41.24% for a multi-view pixel-voting baseline.

Multi-view 3D vision-language models split a scene into 32 views and produce more than six thousand visual tokens, making inference expensive. GeoGR compresses at two levels: at the projector it consolidates cross-view observations into voxel tokens selected by semantic saliency and spatial coverage, merging unselected voxel features into contextual anchors; inside the LLM it computes visual tokens only within a middle-layer window, letting low-relevance tokens skip whole layers with hidden states preserved and rejoin at anchor layers. On LLaVA-OneVision-7B and Video-3D LLM-7B it retains 95.2% and 96.8% of the dense models' performance, with clear LLM prefill and time-to-first-token speedups.

Multi-view 3D vision-language models split a scene into 32 views and produce more than six thousand visual tokens, making inference expensive. GeoGR compresses at two levels: at the projector it consolidates cross-view observations into voxel tokens selected by semantic saliency and spatial coverage, merging unselected voxel features into contextual anchors; inside the LLM it computes visual tokens only within a middle-layer window, letting low-relevance tokens skip whole layers with hidden states preserved and rejoin at anchor layers. On LLaVA-OneVision-7B and Video-3D LLM-7B it retains 95.2% and 96.8% of the dense models' performance, with clear LLM prefill and time-to-first-token speedups.