arXiv:2606. 19733v1 Announce Type: cross Abstract: Efficiently retrieving specific 3D instances from large-scale scenes via natural language prompts remains a formidable challenge in multimedia analysis.
Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.
Open vocabulary 3D scene understanding is essential for next-generation interactive systems, empowering users to intuitively query and navigate reconstructed environments using natural language. However, current 3D Gaussian frameworks are often bottlenecked by restrictive multiview capture requirements, costly scene-specific optimization, and the massive memory overhead of storing dense language features.
arXiv:2509. 24528v4 Announce Type: replace-cross Abstract: Object retrieval from a scene has become a new trend of research due to its numerous applications.
arXiv:2607. 06620v1 Announce Type: cross Abstract: Recent Multimodal Large Language Models (MLLMs) struggle to bridge the representational gap between 2D semantic understanding and 3D spatial geometry.
Recent advancements in 3D Gaussian Splatting (3DGS) have enabled language-guided scene understanding. However, existing Referring 3D Gaussian Splatting (R3DGS) methods are fundamentally restricted to single-target queries.
arXiv:2607. 08541v1 Announce Type: cross Abstract: Open-vocabulary object detection and segmentation aim to recognize arbitrary objects beyond predefined categories.
arXiv:2606. 08014v1 Announce Type: cross Abstract: Accurate 3D instance segmentation in point cloud data is critical for machine vision applications.