Thanh-Khoi Nguyen, Thien-Phuc Tran, Minh-Triet Tran · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31293 · open-access PDF
Semantic 3D Gaussian Splatting (3DGS) online memungkinkan pemahaman open-vocabular scene dari pengamatan streaming. Namun, metode yang ada memulihkan konteks geometris yang hilang dari fitur semantik yang berasal dari gambar menggunakan jaringan 3D yang dipelajari tambahan, menyebabkan pelatihan tambahan dan waktu runtime overhead. Kami mencatat bahwa bukti geometris-semantik seperti itu mungkin sudah ada dalam sejarah pengamatan agen dan dapat diambil alih-alih dipelajari. Berdasarkan wawasan ini, kami memperkenalkan RecallGS (Geometry-Grounded Recall for Online Semantic Gaussian Splatting), mekanisme ringan, bebas pelatihan
Machine translation (Meta M2M100); the English original follows.
Online semantic 3D Gaussian Splatting (3DGS) enables open-vocabulary scene understanding from streaming observations. However, existing methods recover geometric context missing from image-derived semantic features using an additionally learned 3D network, incurring extra training and runtime overhead. We observe that such geometric-semantic evidence may already exist in the agent's observation history and can be retrieved rather than learned. Based on this insight, we introduce RecallGS (Geometry-Grounded Recall for Online Semantic Gaussian Splatting), a lightweight, training-free mechanism t
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.31293, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange