Related papers: Self-SuperFlow: Self-supervised Scene Flow Predict…
We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement.…
Point cloud scene flow estimation is of practical importance for dynamic scene navigation in autonomous driving. Since scene flow labels are hard to obtain, current methods train their models on synthetic data and transfer them to real…
Popular benchmarks for self-supervised LiDAR scene flow (stereoKITTI, and FlyingThings3D) have unrealistic rates of dynamic motion, unrealistic correspondences, and unrealistic sampling patterns. As a result, progress on these benchmarks is…
Self-supervised feed-forward methods for scene flow estimation offer real-time efficiency, but their supervision from two-frame point correspondences is unreliable and often breaks down under occlusions. Multi-frame supervision has the…
Unsupervised deep learning for optical flow computation has achieved promising results. Most existing deep-net based methods rely on image brightness consistency and local smoothness constraint to train the networks. Their performance…
In this paper, we present a new self-supervised scene flow estimation approach for a pair of consecutive point clouds. The key idea of our approach is to represent discrete point clouds as continuous probability density functions using…
Optical flow is an indispensable building block for various important computer vision tasks, including motion estimation, object tracking, and disparity measurement. In this work, we propose TransFlow, a pure transformer architecture for…
It has been recently shown that a convolutional neural network can learn optical flow estimation with unsupervised learning. However, the performance of the unsupervised methods still has a relatively large gap compared to its supervised…
Efficiently selecting an appropriate spike stream data length to extract precise information is the key to the spike vision tasks. To address this issue, we propose a dynamic timing representation for spike streams. Based on multi-layers…
Recently, neural network for scene flow estimation show impressive results on automotive data such as the KITTI benchmark. However, despite of using sophisticated rigidity assumptions and parametrizations, such networks are typically…
Self-supervised representation learning is able to learn semantically meaningful features; however, much of its recent success relies on multiple crops of an image with very few objects. Instead of learning view-invariant representation…
Scene flow is the task of estimating 3D motion vectors to individual points of a dynamic 3D scene. Motion vectors have shown to be beneficial for downstream tasks such as action classification and collision avoidance. However, data…
State-of-the-art scene flow algorithms pursue the conflicting targets of accuracy, run time, and robustness. With the successful concept of pixel-wise matching and sparse-to-dense interpolation, we push the limits of scene flow estimation.…
Automating video-based data and machine learning pipelines poses several challenges including metadata generation for efficient storage and retrieval and isolation of key-frames for scene understanding tasks. In this work, we present two…
Unsupervised optical flow estimation is especially hard near occlusions and motion boundaries and in low-texture regions. We show that additional information such as semantics and domain knowledge can help better constrain this problem. We…
Estimating 3D occupancy and motion at the vehicle's surroundings is essential for autonomous driving, enabling situational awareness in dynamic environments. Existing approaches jointly learn geometry and motion but rely on expensive 3D…
Self-supervised deep learning-based 3D scene understanding methods can overcome the difficulty of acquiring the densely labeled ground-truth and have made a lot of advances. However, occlusions and moving objects are still some of the major…
Event-based cameras have shown great promise in a variety of situations where frame based cameras suffer, such as high speed motions and high dynamic range scenes. However, developing algorithms for event measurements requires a new class…
Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…
We propose to modify the common training protocols of optical flow, leading to sizable accuracy improvements without adding to the computational complexity of the training process. The improvement is based on observing the bias in sampling…