发表机构
Shanghai Jiao Tong University; Alpha Labs, Goertek（上海交通大学; 歌尔股份有限公司Alpha Labs）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
提出一种基于重投影和选择性补丁的二维高斯泼溅双目渲染方法，在保持轻微质量损失的同时，显著降低渲染时间和内存开销。
AI 中文摘要
双目渲染需要对同一场景的两个邻近视角进行渲染，因此会重复大量的可见性计算和着色工作。我们提出了一种二维高斯泼溅（2DGS）流水线，该流水线完整渲染主眼RGB图像和一幅经alpha加权的深度代理图，将该图像重投影到附属眼，并修复未覆盖的像素。小的内部间隙通过插值填补，而较大的遮挡区域则被识别为感兴趣区域（ROIs）并进行选择性重新渲染。深度代理图复用主眼光栅化期间计算出的alpha混合权重，从而避免了单独的深度渲染通道。一个自适应ROI生成器利用重投影图像边界和可选的连通中心孔检测来定位所需的更新。在DTU、Tanks and Temples和MipNeRF-360数据集上，该方法将顺序双通道双目参考的测量时间减少了15.5%至28.8%，峰值GPU内存减少了6%至11%。相应的附属眼质量下降最多为1.3 dB PSNR、0.02 SSIM和0.02 LPIPS，这代表了一种可测量的权衡，需要针对具体应用进行感知验证。这些结果为受控静态场景立体渲染建立了一种实用的效率-质量权衡，并激励在连续运动条件下及物理VR硬件上进行未来评估。
英文摘要
Binocular rendering requires two nearby views of the same scene and therefore repeats substantial visibility and shading work. We present a 2D Gaussian Splatting (2DGS) pipeline that fully renders a dominant-eye RGB image and an alpha-weighted depth proxy, reprojects that image to the affiliated eye, and repairs uncovered pixels. Small interior gaps are interpolated, whereas larger disoccluded regions are identified as regions of interest (ROIs) and selectively re-rendered. The depth proxy reuses the alpha-blending weights computed during dominant-eye rasterization, avoiding a separate depth-rendering pass. An adaptive ROI generator localizes the required updates using reprojected image boundaries and optional connected center-hole detection. On DTU, Tanks and Temples, and MipNeRF-360, the method reduces the measured time of a sequential two-pass binocular reference by 15.5\% to 28.8\% and peak GPU memory by 6\% to 11\%. The corresponding affiliated-eye quality degradation is at most 1.3 dB PSNR, 0.02 SSIM, and 0.02 LPIPS, representing a measurable trade-off that requires application-specific perceptual validation. These results establish a practical efficiency-quality trade-off for controlled static-scene stereo rendering and motivate future evaluation under continuous motion and on physical VR hardware.
