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:2608.22740v1 Announce Type: new
Abstract: Generalizable 3D Gaussian Splatting (G-3DGS) has emerged as a promising approach for novel view synthesis undersparse-view settings. However, existing...
By Zeyang Bai, Yunpeng Wang, Yunbiao Wang, Jun Xiao
arXiv:2608.21136v1 Announce Type: new
Abstract: Recently, open-vocabulary zero-shot 3D scene understanding using vision foundation models has emerged as a promising alternative to data-intensive supe...
By Jie Xu, Na Zhao
ExtrinSplat is a new framework that separates geometry from semantics in 3D Gaussian Splatting scenes. It clusters Gaussians into overlapping 3D object groups and uses a Vision‑Language Model to generate lightweight textual hypotheses, creating an extrinsic index layer that handles complex polysemy. This approach reduces adaptation time from hours to minutes, cuts storage overhead by orders of magnitude, and outperforms existing embedding‑based methods on open‑vocabulary 3D object selection and semantic segmentation benchmarks.
By Jiayu Ding, Xinpeng Liu, Zhiyi Pan, Shiqiang Long, Ge Li
PePESeg3D introduces perception priors into a multi‑scale 3D Gaussian segmentation pipeline, integrating monocular depth and mask constraints during geometry reconstruction and dense depth‑color cues with view‑consistent centroid supervision during contrastive feature learning. This dual‑stage approach aligns geometry with semantic structure and compensates for incomplete mask supervision from 2D foundation models. Experiments on SPIn‑NeRF, LERF‑Mask, and NVOS benchmarks show state‑of‑the‑art performance in both multi‑scale segmentation and scene reconstruction.
By Sungjae Choi, Seunghee Koh, Junmo Kim
LucidLyra is a framework that reconstructs 3D scenes from video latents in a feed‑forward manner while simultaneously providing open‑vocabulary semantics and instance cues. By distilling knowledge from a camera‑controlled video diffusion model and frozen 2D vision foundation models, it jointly infers 3D Gaussians that encode geometry, appearance, and semantic information without requiring per‑scene optimization or manual 3D annotations. The resulting scenes support novel‑view rendering, open‑vocabulary segmentation, and object grouping, and can be extended to monocular video for dynamic 3D reconstruction.