Many estimation, planning, and optimal control problems in robotics have an optimization
problem at their core. In most of these optimization problems, the objective to be maximized …

Abstract We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network
architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D …

We present Theseus, an efficient application-agnostic open source library for differentiable
nonlinear least squares (DNLS) optimization built on PyTorch, providing a common …

Camera pose estimation in known scenes is a 3D geometry task recently tackled by multiple
learning algorithms. Many regress precise geometric quantities, like poses or 3D points …

Finding local features that are repeatable across multiple views is a cornerstone of sparse
3D reconstruction. The classical image matching paradigm detects keypoints per-image …

We present a fast feature-metric point cloud registration framework, which enforces the
optimisation of registration by minimising a feature-metric projection error without …

Virtual reality, augmented reality, robotics, and autonomous driving have attracted much
attention from the academic and industrial communities, in which visual SLAM (VSLAM) is a …

Almost all previous deep learning-based multi-view stereo (MVS) approaches focus on
improving reconstruction quality. Besides quality, efficiency is also a desirable feature for …

Abstract We present Recurrent Fitting (ReFit), a neural network architecture for single-image,
parametric 3D human reconstruction. ReFit learns a feedback-update loop that mirrors the …

We address the generalization ability of recent learning-based point cloud registration
methods. Despite their success, these approaches tend to have poor performance when …