CLEAR: Conflict-aware Learning via Evidence-guided Adaptive Routing for Unified Sparse-View 3D Gaussian Super-Resolution
2026-08-03 • Computer Vision and Pattern Recognition
Computer Vision and Pattern Recognition
AI summaryⓘ
The authors address a tough problem of improving 3D images when only sparse and low-resolution views are available, which usually makes it hard to get clear details. They propose CLEAR, a new method that combines the steps of reconstruction and refinement into one process to avoid errors that pile up in older two-step methods. Their approach smartly balances information from low-resolution data and high-resolution hints, correcting conflicts during training and focusing on important details. Tests show that CLEAR produces sharper and more accurate 3D images compared to previous techniques.
3D Gaussian SplattingSparse-view Super-resolutionLow-resolution ReconstructionHigh-frequency DetailsGradient ConflictAdaptive RoutingPatch-to-Gaussian MappingGaussian DropoutGeometric FidelityRendering Quality
Authors
Hantang Li, Qiang Zhu, Xiandong Meng, Debin Zhao, Xiaopeng Fan
Abstract
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.