AI 中文总结
针对稀疏视图三维高斯超分辨率的误差累积问题，提出首个统一单阶段框架CLEAR，通过冲突感知优化、证据引导路由等技术，在4×超分辨率基准上实现了最优渲染质量与几何保真度。
AI 中文摘要
稀疏视图三维高斯溅射超分辨率极具挑战性，因为稀疏且低分辨率（LR）输入缺乏足够的几何与高频信息以实现精确重建。现有稀疏视图超分辨率方法遵循两阶段流程，先执行低分辨率高斯重建，再进行高分辨率（HR）高斯细化，这直接导致了阶段间高斯传递与重建误差累积。为此，我们提出CLEAR，即证据引导自适应路由的冲突感知学习，是首个面向稀疏视图三维高斯溅射超分辨率的统一单阶段框架。具体而言，CLEAR在统一高斯表示内对真实低分辨率观测与外部高分辨率先验进行联合优化。为缓解训练期间稀疏监督引入的梯度冲突，我们提出了逐高斯冲突感知优化策略，将低分辨率梯度视为可靠锚点，仅对严重的高分辨率冲突应用证据条件软修正。此外，为恢复高频细节，我们引入证据引导的块到高斯路由机制，该机制估计块可靠性与细节需求，将其提升至高斯空间，并选择性路由高频梯度与致密化。最后，我们采用共享高斯弃权（不执行）与分离的训练中锚定来增强训练框架的鲁棒性。在合成与真实世界4×超分辨率基准上的大量实验表明，CLEAR始终实现了最先进的渲染质量与优异的几何保真度。
英文摘要
Sparse-view 3D Gaussian Splatting Super-resolution is highly challenging since the sparse and low-resolution (LR) inputs lack sufficient geometric and high-frequency information for accurate reconstruction. To achieve high-quality reconstruction, existing sparse-view super-resolution methods adhere to two-stage pipeline that performs LR Gaussian reconstruction and then high-resolution (HR) Gaussian refinement, which directly results in stage-wise Gaussian transfer and reconstruction error accumulation. To this end, we propose CLEAR, a Conflict-aware Learning via Evidence-guided Adaptive Routing, as the first unified single-stage framework for Sparse-view 3D Gaussian Splatting Super-resolution. Specifically, CLEAR performs joint the optimization of authentic LR observations and external HR priors within a unified Gaussian representation. To mitigate the gradient conflicts introduced by sparse supervision during training, we propose a Gaussian-wise conflict-aware optimization strategy that regards the LR gradient as a reliable anchor and applies evidence-conditioned soft correction only to severe HR conflicts. Moreover, to recover high-frequency details, we introduce an evidence-guided Patch-to-Gaussian routing mechanism which estimates patch reliability and detail demand, lifts them into Gaussian space, and selectively routes high-frequency gradients and densification. Finally, we employ shared Gaussian dropout and a detached mid-training anchoring to enhance the robustness of training framework. Extensive experiments on both synthetic and real-world $4\times$ super-resolution benchmarks demonstrate that CLEAR consistently achieves state-of-the-art rendering quality and superior geometric fidelity.
Comments9 pages, 5 figures
