We present a method to perform novel view and time synthesis of dynamic scenes, requiring
only a monocular video with known camera poses as input. To do this, we introduce Neural …

We propose a novel end-to-end deep scene flow model, called PointPWC-Net, that directly
processes 3D point cloud scenes with large motions in a coarse-to-fine fashion. Flow …

Multi-frame depth estimation improves over single-frame approaches by also leveraging
geometric relationships between images via feature matching, in addition to learning …

Before the deep learning revolution, many perception algorithms were based on runtime
optimization in conjunction with a strong prior/regularization penalty. A prime example of this …

Autonomous systems possess the features of inferring their own state, understanding their
surroundings, and performing autonomous navigation. With the applications of learning …

Recently, several frameworks for self-supervised learning of 3D scene flow on point clouds
have emerged. Scene flow inherently separates every scene into multiple moving agents …

This work proposes a novel approach to 4D radar-based scene flow estimation via cross-
modal learning. Our approach is motivated by the co-located sensing redundancy in modern …

Abstract 3D scene flow estimation from point clouds is a low-level 3D motion perception task
in computer vision. Flow embedding is a commonly used technique in scene flow estimation …

Recently, the RGB images and point clouds fusion methods have been proposed to jointly
estimate 2D optical flow and 3D scene flow. However, as both conventional RGB cameras …

We present STaR, a novel method that performs Self-supervised Tracking and
Reconstruction of dynamic scenes with rigid motion from multi-view RGB videos without any …