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 …

Monocular depth estimation is scale-ambiguous, and thus requires scale supervision to
produce metric predictions. Even so, the resulting models will be geometry-specific, with …

Self-supervised monocular depth estimation has been widely studied recently. Most of the
work has focused on improving performance on benchmark datasets, such as KITTI, but has …

Dense 3D reconstruction and ego-motion estimation are key challenges in autonomous
driving and robotics. Compared to the complex, multi-modal systems deployed today, multi …

Multi-frame depth estimation generally achieves high accuracy relying on the multi-view
geometric consistency. When applied in dynamic scenes, eg, autonomous driving, this …

Learning accurate depth is essential to multi-view 3D object detection. Recent approaches
mainly learn depth from monocular images, which confront inherent difficulties due to the ill …

This work addresses the challenge of video depth estimation, which expects not only per-
frame accuracy but, more importantly, cross-frame consistency. Instead of directly …

In this work we introduce ProMotion a unified prototypical transformer-based framework
engineered to model fundamental motion tasks. ProMotion offers a range of compelling …

Self-supervised multi-frame depth estimation achieves high accuracy by computing
matching costs of pixel correspondences between adjacent frames, injecting geometric …

Recent advances in neural reconstruction using posed image sequences have made
remarkable progress. However, due to the lack of depth information, existing volumetric …