发表机构
School of Artificial Intelligence, University of Chinese Academy of Sciences; Global Institute of Future Technology, Shanghai Jiao Tong University（中国科学院大学人工智能学院; 上海交通大学全球未来技术研究院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
本文提出新型通用三维高斯溅射框架SeeU，通过跨视图熵感知模块与条件高斯变换器优化高斯估计，在稀疏视图场景下提升新视图合成的渲染质量与结构完整性，外推设置下PSNR较SOTA方法提升2.44 dB。
AI 中文摘要
通用三维高斯溅射（G-3DGS）是稀疏视图场景下新视图合成的有前景方法，但现有框架受限于像素对齐的高斯估计，在部分观测或遮挡区域表现不佳，常导致表面不完整或结构崩溃。为解决这些挑战，本文提出SeeU（看见不可见），一种新型G-3DGS框架，核心设计为高斯空间中的语义条件细化（Semantic-in-Gaussian）。具体而言，本文引入跨视图熵感知（CEA）模块，将多视图语义与几何线索聚合为紧凑嵌入，这些嵌入指导条件高斯变换器对粗高斯进行残差更新，帮助恢复部分观测结构的欠约束区域，同时保持表面一致性。在多个基准上的全面实验表明，SeeU在保持高效前馈推理的同时，持续提升渲染质量与结构完整性；尤其在具有挑战性的外推设置下，SeeU相比近期SOTA G-3DGS方法实现了平均2.44 dB的PSNR提升。
英文摘要
Generalizable 3D Gaussian Splatting (G-3DGS) has emerged as a promising approach for novel view synthesis undersparse-view settings. However, existing frameworks remain restricted by pixel-aligned Gaussian estimation, whichstruggles in partially observed or occluded regions and often leads to incomplete surfaces or structural collapse. Toaddress these challenges, we propose SeeU (Seeing the Unseen), a novel G-3DGS framework. We frame its core design asSemantic-in-Gaussian: semantic-conditioned refinement in Gaussian space. Specifically, we introduce a Cross-viewEntropy-Aware (CEA) module that aggregates multi-view semantic and geometric cues into compact embeddings. Theseembeddings guide the Conditional Gaussian Transformer, which applies residual updates to coarse Gaussians, helpingrecover under-constrained regions of partially observed structures while preserving surface consistency. Comprehensiveexperiments on multiple benchmarks demonstrate that SeeU consistently improves rendering quality and structuralcompleteness while retaining efficient feed-forward inference. Especially under challenging extrapolation settings,SeeU achieves an average improvement of 2.44 dB in PSNR compared to recent SOTA G-3DGS methods.
CommentsAccepted at the ECCV 2026 Workshop on 3DWM
