Geometric Correspondence Fields: Learned Differentiable Rendering for 3D Pose Refinement in the Wild

European Conference on Computer Vision(2020)

引用 10|浏览261
暂无评分
摘要
We present a novel 3D pose refinement approach based on differentiable rendering for objects of arbitrary categories in the wild. In contrast to previous methods, we make two main contributions: First, instead of comparing real-world images and synthetic renderings in the RGB or mask space, we compare them in a feature space optimized for 3D pose refinement. Second, we introduce a novel differentiable renderer that learns to approximate the rasterization backward pass from data instead of relying on a hand-crafted algorithm. For this purpose, we predict deep cross-domain correspondences between RGB images and 3D model renderings in the form of what we call geometric correspondence fields. These correspondence fields serve as pixel-level gradients which are analytically propagated backward through the rendering pipeline to perform a gradient-based optimization directly on the 3D pose. In this way, we precisely align 3D models to objects in RGB images which results in significantly improved 3D pose estimates. We evaluate our approach on the challenging Pix3D dataset and achieve up to 55% relative improvement compared to state-of-the-art refinement methods in multiple metrics.
更多
查看译文
关键词
pose refinement,geometric correspondence fields,differentiable rendering,3d
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要