CoRoGS：面向鲁棒大偏差视角合成的上下文高斯泼溅
CoRoGS: Contextual Gaussian Splatting for Robust Large-Deviation View Synthesis
将高斯泼溅中的高斯图元视为图节点，通过消息传递建模高斯间依赖关系，并采用渐进式图扩展策略自适应增删高斯，从而在大视角偏差下保持几何一致性；该思路可迁移到任何需要结构化场景表示的NVS任务中。
原文依据 constructing a 3D Gaussian graph, which propagates relational geometry and semantics via message passing
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论大视角偏差下的新视角合成（NVS）仍是3D高斯泼溅（3DGS）中一个尚未充分探索的挑战。在训练覆盖有限的城市场景中，模型在推断到未见视角时往往无法保持几何一致性，导致严重畸变和渲染质量下降。我们提出上下文感知高斯泼溅（CoRoGS），一个面向鲁棒大偏差新视角合成（LD-NVS）的上下文感知框架，将上下文推理嵌入3DGS。CoRoGS不将高斯视为独立的图元，而是采用一种显式建模高斯间依赖关系的上下文公式化表示。该表示通过构建3D高斯图实现，该图通过消息传递传播关系几何与语义，从而产生上下文感知的高斯更新。为了在显著视角偏差下进一步保持结构一致性，我们引入渐进式图扩展策略，自适应地增长和修剪高斯，从而获得更连贯、更完整的场景重建。大量实验表明，CoRoGS优于最优的基于3DGS的方法，产生更高质量的结果。我们强调，CoRoGS能够鲁棒地处理广泛的视角偏移，包括横向偏差（如车道级偏移）以及跨层级转换，例如从地面驾驶视角到俯视视角。
英文原文摘要 1434 字符
Novel view synthesis (NVS) under large view deviations remains an underexplored challenge for 3D Gaussian Splatting (3DGS). In urban scenes with limited training coverage, models often fail to maintain geometric consistency when extrapolating to unseen viewpoints, resulting in severe distortions and degraded rendering quality. We introduce Context-Aware Gaussian Splatting (CoRoGS), a Context-aware framework for Robust large-deviation novel view synthesis (LD-NVS) that embeds contextual reasoning into 3DGS. Instead of treating Gaussians as independent primitives, CoRoGS adopts a contextual formulation that explicitly models inter-Gaussian dependencies. This representation is implemented by constructing a 3D Gaussian graph, which propagates relational geometry and semantics via message passing, resulting in context-aware Gaussian updates. To further maintain structural consistency under substantial view deviation, we incorporate a progressive graph expansion strategy that adaptively grows and prunes Gaussians, leading to more coherent and complete scene reconstructions. Extensive experiments demonstrate that CoRoGS outperforms state-of-the-art 3DGS-based methods, producing higher-quality results. We highlight that CoRoGS robustly handles a wide range of view shifts, including lateral deviations (e.g., lane-level offsets) and cross-level transitions such as from ground-level driving views to elevated perspectives.