# ICLR 2026 paper SAGE-3D adds collision and semantics to 3DGS scenes to support vision-language navigation

- Source: 3D视觉工坊 · 微信公众号
- Published: 2026-10-31T16:00:00.000Z
- RoboHot: https://robohot.news/en/items/wn0jd4crp75pjqo5n2kxjrdsx
- Original: https://mp.weixin.qq.com/s?__biz=MzU1MjY4MTA1MQ==&mid=2247752733&idx=1&sn=64259d1a71ce04f782210bd5efca9832&chksm=fa9332e6af1fbf7627683f0984d9c76ec3ea3103d12618ba3b2a0036d4f82212f544894643b6&scene=126&sessionid=1793529027#rd

## Summary

The ICLR 2026 paper SAGE-3D proposes decoupling and assembling 3DGS rendering, source-mesh collision bodies, and manual semantic annotations into an executable navigation environment, modeled as a semantics- and physics-enhanced POMDP. Its object-level semantic anchoring provides category, instance ID, and bounding box, while physics-aware execution assembles collision bodies extracted from source meshes via CoACD convex decomposition and embeds them into the 3DGS scene.