Nov 2026· Proceedings of the 34th ACM International Conference on Multimedia· pp. 10296-10305· 0 citations
Abstract
3D Gaussian Splatting (3DGS) has recently achieved impressive performance in novel view synthesis and real-time rendering. However, its geometric reconstruction quality in indoor scenes remains limited, especially in large weak-texture regions such as walls, ceilings, and floors, where sparse initialization and purely photometric supervision often lead to floaters, distorted surfaces, and structural ambiguities. To address this issue, we propose a planar prior guided 3D Gaussian Splatting framework for indoor scene reconstruction. Our method first extracts dense geometric priors, including depth and normal maps, from input images to provide robust structural guidance for optimization. Based on these priors, we further construct planar priors through multi-granularity image segmentation and geometric consistency verification, enabling reliable identification of planar regions in complex indoor scenes. We then incorporate region-aware geometric optimization into the 3DGS pipeline, including planar region constraints, non-planar local geometric regularization, and global geometry supervision, to jointly improve structural fidelity and surface consistency. Extensive experiments on multiple indoor datasets demonstrate that the proposed method produces more accurate meshes and more faithful rendering results than recent 3DGS-based baselines, particularly in weak-texture and piecewise-planar areas.
A lightweight gradient-driven point allocation strategy for depth-guided Gaussian splatting that bypasses traditional Structure-from-Motion initialization and incorporates a bidirectional re-projection check to eliminate transient noise and occlusions, ensuring geometric consistency is proposed.
Yu-Hao Shang, Zhen-Shen Qu, Guan-Yi Rong et al.· SAE technical paper series· 0 citations
D3GS is proposed, a Depth-DINO-Diffusion guided sparse-view Gaussian reconstruction framework that jointly enhances geometry and appearance and injects generative priors into an iterative optimization strategy, enhancing high-frequency geometric and appearance details within the Gaussian representation.
Yun-Qi Gao, Zhan-Feng Liao, Han-Zhang Tu et al.· arXiv.org· 0 citations
This work introduces a geometry-aware cost volume that injects relative pose distance, view-dependent ray angle, and spatial validity masks into dense depth matching, enabling the network to jointly reason about photometric consistency, triangulation reliability, and visibility.
Prized for its high-quality real-time rendering, 3D Gaussian Splatting is a key novel view synthesis technology for fields such as virtual reality and autonomous driving, where it is widely used for outdoor scene reconstruction. However, extensive unbounded and texture-scarce regions in outdoor scenes, such as the sky,...
Jian Xiong, Qing Zhang, Jiu-Cheng Xie et al.· Proceedings of the 34th ACM...· 0 citations
Reconstructing 3D scenes from sparse views without per-scene optimization remains highly challenging, especially for recovering accurate geometry and fine textures. While recent feedforward approaches leverage generalizable 3D Gaussian Splatting (3DGS) for scene generation, they typically assign one or multiple Gaussia...
Bing He, Jing-Nan Gao, Yu-Nuo Chen et al.· 0 citations
This paper proposes a novel iterative refinement framework based on a video diffusion model to improve the completeness and consistency of dynamic 4D scenes, and substantially outperforms existing baselines.