Related papers: Self-Supervised Monocular Scene Flow Estimation

Computing optical flow is a fundamental problem in computer vision. However, deep learning-based optical flow techniques do not perform well for non-rigid movements such as those found in faces, primarily due to lack of the training data…

Scene flow represents the 3D motion of every point in the dynamic environments. Like the optical flow that represents the motion of pixels in 2D images, 3D motion representation of scene flow benefits many applications, such as autonomous…

Accurate perception of the dynamic environment is a fundamental task for autonomous driving and robot systems. This paper introduces Let Occ Flow, the first self-supervised work for joint 3D occupancy and occupancy flow prediction using…

Dense depth estimation from a single image is a key problem in computer vision, with exciting applications in a multitude of robotic tasks. Initially viewed as a direct regression problem, requiring annotated labels as supervision at…

Recent work in unsupervised multi-object segmentation shows impressive results by predicting motion from a single image despite the inherent ambiguity in predicting motion without the next image. On the other hand, the set of possible…

Convolutional Neural Networks (CNNs) need large amounts of data with ground truth annotation, which is a challenging problem that has limited the development and fast deployment of CNNs for many computer vision tasks. We propose a novel…

Existing self-supervised monocular depth estimation methods can get rid of expensive annotations and achieve promising results. However, these methods suffer from severe performance degradation when directly adopting a model trained on a…

The field of neuromorphic computing promises extremely low-power and low-latency sensing and processing. Challenges in transferring learning algorithms from traditional artificial neural networks (ANNs) to spiking neural networks (SNNs)…

Recent work has shown that optical flow estimation can be formulated as a supervised learning task and can be successfully solved with convolutional networks. Training of the so-called FlowNet was enabled by a large synthetically generated…

A single color image can contain many cues informative towards different aspects of local geometric structure. We approach the problem of monocular depth estimation by using a neural network to produce a mid-level representation that…

3D motion estimation including scene flow and point cloud registration has drawn increasing interest. Inspired by 2D flow estimation, recent methods employ deep neural networks to construct the cost volume for estimating accurate 3D flow.…

The video and action classification have extremely evolved by deep neural networks specially with two stream CNN using RGB and optical flow as inputs and they present outstanding performance in terms of video analysis. One of the…

Scene flow is a challenging task aimed at jointly estimating the 3D structure and motion of the sensed environment. Although deep learning solutions achieve outstanding performance in terms of accuracy, these approaches divide the whole…

Despite advancements in self-supervised monocular depth estimation, challenges persist in dynamic scenarios due to the dependence on assumptions about a static world. In this paper, we present Manydepth2, to achieve precise depth estimation…

Self-supervised depth estimation for indoor environments is more challenging than its outdoor counterpart in at least the following two aspects: (i) the depth range of indoor sequences varies a lot across different frames, making it…

We introduce MGNet, a multi-task framework for monocular geometric scene understanding. We define monocular geometric scene understanding as the combination of two known tasks: Panoptic segmentation and self-supervised monocular depth…

Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…

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 autonomous vehicles. Such redundancy implicitly provides various…

Depth-aware video panoptic segmentation tackles the inverse projection problem of restoring panoptic 3D point clouds from video sequences, where the 3D points are augmented with semantic classes and temporally consistent instance…

Perceiving and understanding 3D motion is a core technology in fields such as autonomous driving, robots, and motion prediction. This paper proposes a 3D motion perception method called ScaleFlow++ that is easy to generalize. With just a…