Nowadays, many visual scene understanding problems are addressed by dense prediction networks. But pixel-wise dense annotations are very expensive (e.g., for scene parsing) or impossible (e.g., for intrinsic image decomposition), motivating us to leverage cheap point-level weak supervision. However, existing pointly-supervised methods still use the same architecture designed for full supervision. In stark contrast to them, we propose a new paradigm that makes predictions for point coordinate queries, as inspired by the recent success of implicit representations, like distance or radiance fields. As such, the method is named as dense prediction fields (DPFs). DPFs generate expressive intermediate features for continuous sub-pixel locations, thus allowing outputs of an arbitrary resolution. DPFs are naturally compatible with point-level supervision. We showcase the effectiveness of DPFs using two substantially different tasks: high-level semantic parsing and low-level intrinsic image decomposition. In these two cases, supervision comes in the form of single-point semantic category and two-point relative reflectance, respectively. As benchmarked by three large-scale public datasets PASCALContext, ADE20K and IIW, DPFs set new state-of-the-art performance on all of them with significant margins. Code can be accessed at https://github.com/cxx226/DPF.

翻译：现今，许多视觉场景理解问题通过密集预测网络来解决。但像素级的密集标注成本极高（如场景解析）或不可行（如本征图像分解），这促使我们利用廉价的点级弱监督。然而，现有的点监督方法仍沿用为全监督设计的架构。与此截然不同，受距离场或辐射场等隐式表示近期成功的启发，我们提出了一种新范式，该范式对点坐标查询进行预测，因此命名为密集预测场（DPF）。DPF可为连续亚像素位置生成表达性中间特征，从而支持任意分辨率输出，且天然兼容点级监督。我们通过两种差异显著的任务——高级语义解析与低级本征图像分解——展示了DPF的有效性。在这两种场景中，监督形式分别对应单点语义类别和两点相对反射率。经三大大规模公共数据集PASCAL-Context、ADE20K和IIW的基准测试，DPF以显著优势在所有数据集上刷新了最优性能。代码见https://github.com/cxx226/DPF。