arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2206.03380cs.GRcs.CV
收藏

使用蒙特卡罗渲染和去噪从图像中分解形状、光线和材质

Shape, Light, and Material Decomposition from Images using Monte Carlo Rendering and Denoising

NVIDIA(英伟达)

Jon Hasselgren, Nikolai Hofmann, Jacob Munkberg

摘要:

可微分渲染的最新进展使得能够从多视图图像中高质量地重建3D场景。大多数方法依赖于简单的渲染算法:预过滤的直接照明或学习的辐照度表示。我们表明,一个更现实的阴影模型,结合光线追踪和蒙特卡罗集成,大大提高了分解成形状,材料和照明。不幸的是,蒙特卡罗积分提供了显着的噪声估计,即使在大样本计数,这使得基于梯度的逆渲染非常具有挑战性。为了解决这个问题,我们将多个重要性采样和去噪在一个新的逆渲染流水线。这大大提高了收敛性,并在低样本数下实现了基于梯度的优化。我们提出了一种有效的方法来联合重建几何(显式三角形网格),材料和照明,这大大提高了材料和光分离相比,以前的工作。我们认为,去噪可以成为高质量的逆渲染流水线的一个组成部分。

英文摘要:

Recent advances in differentiable rendering have enabled high-quality reconstruction of 3D scenes from multi-view images. Most methods rely on simple rendering algorithms: pre-filtered direct lighting or learned representations of irradiance. We show that a more realistic shading model, incorporating ray tracing and Monte Carlo integration, substantially improves decomposition into shape, materials & lighting. Unfortunately, Monte Carlo integration provides estimates with significant noise, even at large sample counts, which makes gradient-based inverse rendering very challenging. To address this, we incorporate multiple importance sampling and denoising in a novel inverse rendering pipeline. This substantially improves convergence and enables gradient-based optimization at low sample counts. We present an efficient method to jointly reconstruct geometry (explicit triangle meshes), materials, and lighting, which substantially improves material and light separation compared to previous work. We argue that denoising can become an integral part of high quality inverse rendering pipelines.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑