PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.
arXiv preprint arXiv:2603.03283 , year=
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 3years
2026 3verdicts
UNVERDICTED 3roles
background 1polarities
background 1representative citing papers
Coarse four-group semantic color coding (RGBB) appended to point clouds before tokenization improves LLM-based structured indoor prediction on Structured3D, SpatialLM, and ARKitScenes, especially for openings and furniture instances.
MAG-VLAQ fuses multi-modal ground and aerial data via ODE-conditioned vector-of-locally-aggregated-queries to nearly double recall@1 on aerial-ground place recognition benchmarks.
citing papers explorer
-
PAR3D: A Unified 3D-MLLM with Part-Aware Representation for Scene Understanding
PAR3D is a part-aware 3D-MLLM framework with ScenePart dataset, Part-Aware 3D Representation Learning, and Hierarchical Segmentation Query Generation to improve part-level 3D scene understanding.
-
Coarse Semantic Injection for LLM-Conditioned Structured Indoor Prediction
Coarse four-group semantic color coding (RGBB) appended to point clouds before tokenization improves LLM-based structured indoor prediction on Structured3D, SpatialLM, and ARKitScenes, especially for openings and furniture instances.
-
MAG-VLAQ: Multi-modal Aerial-Ground Query Aggregation for Cross-View Place Recognition
MAG-VLAQ fuses multi-modal ground and aerial data via ODE-conditioned vector-of-locally-aggregated-queries to nearly double recall@1 on aerial-ground place recognition benchmarks.