In the realm of modern autonomous driving, the perception system is indispensable for
accurately assessing the state of the surrounding environment, thereby enabling informed …

Abstract Recurrent All-Pairs Field Transforms (RAFT) has shown great potentials in
matching tasks. However, all-pairs correlations lack non-local geometry knowledge and …

The perception of the surrounding environment is a key requirement for autonomous driving
systems, yet the computation of an accurate semantic representation of the scene starting …

We present a unified formulation and model for three motion and 3D perception tasks:
optical flow, rectified stereo matching and unrectified stereo depth estimation from posed …

We introduce Infinigen, a procedural generator of photorealistic 3D scenes of the natural
world. Infinigen is entirely procedural: every asset, from shape to texture, is generated from …

In the field of binocular stereo matching, remarkable progress has been made by iterative
methods like RAFT-Stereo and CREStereo. However, most of these methods lose …

Given sparse depths and the corresponding RGB images, depth completion aims at spatially
propagating the sparse measurements throughout the whole image to get a dense depth …

We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-
quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which …

This paper reports on the NTIRE 2024 challenge on HR Depth From images of Specular and
Transparent surfaces held in conjunction with the New Trends in Image Restoration and …

Despite impressive performance for high-level downstream tasks, self-supervised pre-
training methods have not yet fully delivered on dense geometric vision tasks such as stereo …