360-GeoGS: Geometrically Consistent Feed-Forward 3D Gaussian Splatting Reconstruction for 360 Images

2026-01-05 · Jiaqi Yao, Zhongmiao Yan, Jingyi Xu, Songpengcheng Xia, Yan Xiang, Ling Pei arxiv

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches, though capable of producing high-quality results, require per-scene optimization and lack real-time efficiency. Explicit 3D Gaussian Splatting (3DGS) enables efficient rendering, but most feed-forward variants focus on visual quality rather than geometric consistency, limiting accurate surface reconstruction and overall reliability in spatial perception tasks. This paper presents a novel feed-forward 3DGS framework for 360 images, capable of generating geometrically consistent Gaussian primitives while maintaining high rendering quality. A Depth-Normal geometric regularization is introduced to couple rendered depth gradients with normal information, supervising Gaussian rotation, scale, and position to improve point cloud and surface accuracy. Experimental results show that the proposed method maintains high rendering quality while significantly improving geometric consistency, providing an effective solution for 3D reconstruction in spatial perception tasks.

📄 PDF Abstract BibTeX arXiv:2601.02102

Code (0)

등록된 구현이 없습니다.

Tasks

3D Reconstruction

GeoGS3D: Single-view 3D Reconstruction via Geometric-aware Diffusion Model and Gaussian Splatting

2024-03-15 · Qijun Feng, Zhen Xing, Zuxuan Wu, Yu-Gang Jiang

We introduce GeoGS3D, a novel two-stage framework for reconstructing detailed 3D objects from single-view images. Inspired by the success of pre-trained 2D diffusion models, our method incorporates an orthogonal plane de…

3D Reconstruction Single-View 3D Reconstruction

GeoGS-SLAM: Geometry-Only Gaussian Splatting for Dense Monocular SLAM

2026-07-08 · Lipu Zhou, Yaoyun Kang, Junxiang Pang, Shengkai Sun 외 arxiv

Dense visual SLAM is a fundamental problem in robotics. Recent advances in 3DGS have demonstrated its potential for dense SLAM. Existing 3DGS frameworks focus on both appearance and geometry modeling. However, scene geom…

Novel View Synthesis 3D Reconstruction

GUSH3R: Everyone Everywhere All at Once as Gaussians

2026-07-06 · Keito Abe, Kaede Shiohara, Takashi Otonari, Toshihiko Yamasaki arxiv

Reconstructing dynamic human-scene environments from monocular videos is a challenging problem that requires jointly modeling scene geometry, camera motion, and non-rigid human dynamics while enabling photorealistic rend…

Novel View Synthesis 3D Reconstruction Point Clouds

SketchFaceGS: Real-Time Sketch-Driven Face Editing and Generation with Gaussian Splatting

2026-04-21 · Bo Li, Jiahao Kang, Yubo Ma, Feng-Lin Liu 외 arxiv

3D Gaussian representations have emerged as a powerful paradigm for digital head modeling, achieving photorealistic quality with real-time rendering. However, intuitive and interactive creation or editing of 3D Gaussian …

WorldMirror: Universal 3D World Reconstruction with Any-Prior Prompting

2025-10-12 · Yifan Liu, Zhiyuan Min, Zhenwei Wang, Junta Wu 외 arxiv

We present WorldMirror, an all-in-one, feed-forward model for versatile 3D geometric prediction tasks. Unlike existing methods constrained to image-only inputs or customized for a specific task, our framework flexibly in…

Novel View Synthesis Point Clouds