Self-supervised visual representation learning has seen huge progress recently, but no
large scale evaluation has compared the many models now available. We evaluate the …

Monocular depth prediction plays a crucial role in understanding 3D scene geometry.
Although recent methods have achieved impressive progress in evaluation metrics such as …

Recent advances in large-scale pretraining have yielded visual foundation models with
strong capabilities. Not only can recent models generalize to arbitrary images for their …

Self-supervised learning aims to learn representations from the data itself without explicit
manual supervision. Existing efforts ignore a crucial aspect of self-supervised learning-the …

Learning to predict scene depth from RGB inputs is a challenging task both for indoor and
outdoor robot navigation. In this work we address unsupervised learning of scene depth and …

In this paper, we propose a novel Pattern-Affinitive Propagation (PAP) framework to jointly
predict depth, surface normal and semantic segmentation. The motivation behind it comes …

In this work we train in an end-to-end manner a convolutional neural network (CNN) that
jointly handles low-, mid-, and high-level vision tasks in a unified architecture. Such a …

In this paper, we propose Geometric Neural Network (GeoNet) to jointly predict depth and
surface normal maps from a single image. Building on top of two-stream CNNs, our GeoNet …

Pixel-level labelling tasks, such as semantic segmentation, play a central role in image
understanding. Recent approaches have attempted to harness the capabilities of deep …

In this paper we address three different computer vision tasks using a single basic
architecture: depth prediction, surface normal estimation, and semantic labeling. We use a …