arXiv:2604.09045v2 Announce Type: replace
Abstract: Recent works on 3D scene understanding leverage 2D masks from visual foundation models (VFMs) to supervise radiance fields, enabling instance-level...
By Tsuheng Hsu, Guiyu Liu, Juho Kannala, Janne Heikkil\"a
GaussianDS introduces a depth‑supervised framework for 3D Gaussian Splatting that jointly optimizes RGB appearance, depth, and compact semantics from scratch. By arranging multi‑view images into a pose‑aware pseudo‑video and propagating view‑consistent masks via SAM2, the method aligns semantic lifting with geometric cues, using depth supervision and edge‑aware refinement to curb semantic drift and boundary leakage. The approach achieves state‑of‑the‑art performance on LERF and 3D‑OVS benchmarks while preserving high‑fidelity reconstruction and enabling downstream tasks such as 3D object removal.
By Yufei Zhang, Chenlu Zhan, Hongwei Wang
The paper introduces 3D Morphological Perturbations, an optimization‑free regularizer for 3D representations such as NeRF and 3D Gaussian Splatting. By treating each Gaussian as a pixel‑like element, the method applies scale, rotation, and pruning perturbations to preserve spatial consistency across views, eliminating the need for per‑scene optimization during dataset curation. Experiments on a lightweight video diffusion sandbox and a 14B‑parameter video model show that the approach improves geometric priors, reduces mean depth error by 12.5% over state‑of‑the‑art 3D artifact refiners, and boosts downstream robotics policy success rates by up to 8.0% on three manipulation tasks.
By Onat \c{S}ahin, Mohammad Altillawi, George Eskandar, Carlos Carbone, Ziyuan Liu
PointGauss is a 3D-native framework that performs semantic parsing and instance segmentation on 3D Gaussian splatting representations by treating Gaussian primitives as unstructured point sets and extracting scale‑invariant geometric features with Point Transformer V3. It introduces an adaptive region‑of‑interest cropping strategy and an instance‑aware distance‑constrained rasterization pipeline to enable scalable, view‑consistent pixel‑level projections. The authors also release SplatSeg‑360, a cross‑scale benchmark with 32 complex scenes and over 6,300 aligned 2D‑3D masks, and show that PointGauss achieves real‑time performance with state‑of‑the‑art 3D‑mIoU (~90%) and 2D‑mIoU (~80%) scores.
By Wentao Sun, Yiping Chen, John S. Zelek, Jonathan Li
arXiv:2608.30870v1 Announce Type: new
Abstract: Semantic segmentation in 3D Gaussian Splatting (3DGS) is crucial for advancing 3D scene understanding. Existing methods predominantly rely on feature d...
By Kun Cao, Di Wang, Haibin Zhu, Haozhi Huang, Xu Wang, Zheng Shi, Guanghua Yang
Feature Puzzles introduces a framework that learns multi‑view‑consistent 3D‑aware segmentation from only single‑image semantic segmentation supervision. The method creates pseudo‑labels via image cropping and geometric transformations, then uses a lightweight network that leverages pre‑trained 3D foundation models to produce consistent segmentations across views. It supports various prompts, extends to open‑vocabulary segmentation, and achieves state‑of‑the‑art performance on several benchmarks while enabling zero‑shot transfer.
By Jiahao Ma, Qiang Zhang, Miaomiao Liu, David Ahmedt-Aristizabal, Chuong Nguyen
arXiv:2606. 28656v1 Announce Type: cross Abstract: Deformable 3D Gaussian Splatting (3DGS) has emerged as an efficient approach for rendering dynamic scenes in a wide range of 3D applications.
By Ruitao Chen, Mozhang Guo, Jinge Li
The paper introduces Epipolar Distillation (EpiDistill), a method that transfers scale‑aware geometric priors from multi‑view models to monocular depth foundation models using Rectified Stereo Tokens. By preserving epipolar attention patterns, the single‑view model maintains geometric consistency without needing multi‑view inputs during inference. Experiments show significant improvements in zero‑shot metric depth estimation on challenging datasets such as ETH3D and DIODE, and the approach consistently boosts performance of state‑of‑the‑art ViT‑based models like UniDepthV2 and DepthPro.
By Jung-Hee Kim, Xiaoming Liu
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.
The paper introduces HierGF, a method for sparse‑view 3D reconstruction that uses a hierarchical geometry‑perception backbone to generate structured pseudo‑supervision from limited views. It incorporates a learnable confidence network to focus gradients on cross‑view consistent content and a geometrically consistent densification module to improve alignment and fill under‑sampled regions. This approach aims to overcome the challenges of few images and incomplete coverage that typically lead to overfitting and structural holes in existing methods.
By Bi'an Du, Zhimin Zhang, Daizong Liu, Baoquan Chen, Wei Hu
arXiv:2609.22941v1 Announce Type: new
Abstract: Novel view synthesis from sparse inputs remains challenging for 3D Gaussian Splatting (3DGS) due to ambiguous geometry, cross-view inconsistency, and m...
By Yunqi Gao, Zhanfeng Liao, Hanzhang Tu, Zhaoqi Su, Guoqing Zheng, Songtao Wang, Hongwen Zhang, Zhou Xue, Leyuan Liu, Yebin Liu
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