Stereo vision is a flourishing field, attracting the attention of many researchers. Recently,
leveraging on the development of deep learning, stereo matching algorithms have achieved …

Self-supervised monocular depth estimation networks are trained to predict scene depth
using nearby frames as a supervision signal during training. However, for many …

Recently, the ever-increasing capacity of large-scale annotated datasets has led to profound
progress in stereo matching. However, most of these successes are limited to a specific …

Abstract Under good conditions, Neural Radiance Fields (NeRFs) have shown impressive
results on novel view synthesis tasks. NeRFs learn a scene's color and density fields by …

To reduce the human efforts in neural network design, Neural Architecture Search (NAS)
has been applied with remarkable success to various high-level vision tasks such as …

Estimating depth from RGB images is a long-standing ill-posed problem, which has been
explored for decades by the computer vision, graphics, and machine learning communities …

Monocular visual odometry approaches that purely rely on geometric cues are prone to
scale drift and require sufficient motion parallax in successive frames for motion estimation …

Abstract 3D reconstruction of scenes using multiple images, relying on robust
correspondence search and depth estimation, has been thoroughly studied for the two‐view …

Stereo matching algorithms usually consist of four steps, including matching cost calculation,
matching cost aggregation, disparity calculation, and disparity refinement. Existing CNN …

We introduce a novel framework for training deep stereo networks effortlessly and without
any ground-truth. By leveraging state-of-the-art neural rendering solutions, we generate …