Neural scene flow prior

X Li, J Kaesemodel Pontes… - Advances in Neural …, 2021 - proceedings.neurips.cc
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 …

Fast neural scene flow

X Li, J Zheng, F Ferroni, JK Pontes… - Proceedings of the …, 2023 - openaccess.thecvf.com
Abstract Neural Scene Flow Prior (NSFP) is of significant interest to the vision community
due to its inherent robustness to out-of-distribution (OOD) effects and its ability to deal with …

Scene flow to action map: A new representation for rgb-d based action recognition with convolutional neural networks

P Wang, W Li, Z Gao, Y Zhang… - Proceedings of the …, 2017 - openaccess.thecvf.com
Scene flow describes the motion of 3D objects in real world and potentially could be the
basis of a good feature for 3D action recognition. However, its use for action recognition …

Motion-compensated compression of dynamic voxelized point clouds

RL De Queiroz, PA Chou - IEEE Transactions on Image …, 2017 - ieeexplore.ieee.org
Dynamic point clouds are a potential new frontier in visual communication systems. A few
articles have addressed the compression of point clouds, but very few references exist on …

Dense semi-rigid scene flow estimation from rgbd images

J Quiroga, T Brox, F Devernay, J Crowley - Computer Vision–ECCV 2014 …, 2014 - Springer
Scene flow is defined as the motion field in 3D space, and can be computed from a single
view when using an RGBD sensor. We propose a new scene flow approach that exploits the …

A primal-dual framework for real-time dense RGB-D scene flow

M Jaimez, M Souiai… - … on robotics and …, 2015 - ieeexplore.ieee.org
This paper presents the first method to compute dense scene flow in real-time for RGB-D
cameras. It is based on a variational formulation where brightness constancy and geometric …

Development and validation of a Brazilian sign language database for human gesture recognition

TM Rezende, SGM Almeida, FG Guimarães - Neural Computing and …, 2021 - Springer
Sign language recognition is considered the most important and challenging application in
gesture recognition, involving the fields of pattern recognition, machine learning and …

SphereFlow: 6 DoF scene flow from RGB-D pairs

M Hornacek, A Fitzgibbon, C Rother - Proceedings of the IEEE …, 2014 - cv-foundation.org
We take a new approach to computing dense scene flow between a pair of consecutive RGB-
D frames. We exploit the availability of depth data by seeking correspondences with respect …

Re-evaluating lidar scene flow for autonomous driving

N Chodosh, D Ramanan, S Lucey - arxiv preprint arxiv:2304.02150, 2023 - arxiv.org
Popular benchmarks for self-supervised LiDAR scene flow (stereoKITTI, and
FlyingThings3D) have unrealistic rates of dynamic motion, unrealistic correspondences, and …

What test oracle should I use for effective GUI testing?

A Memon, I Banerjee… - 18th IEEE International …, 2003 - ieeexplore.ieee.org
Test designers widely believe that the overall effectiveness and cost of software testing
depends largely on the type and number of test cases executed on the software. In this …