INV-Flow2PoseNet: Light-Resistant Rigid Object Pose from Optical Flow of RGB-D Images using Images, Normals and Vertices

09/14/2022
by   Torben Fetzer, et al.
1

This paper presents a novel architecture for simultaneous estimation of highly accurate optical flows and rigid scene transformations for difficult scenarios where the brightness assumption is violated by strong shading changes. In the case of rotating objects or moving light sources, such as those encountered for driving cars in the dark, the scene appearance often changes significantly from one view to the next. Unfortunately, standard methods for calculating optical flows or poses are based on the expectation that the appearance of features in the scene remain constant between views. These methods may fail frequently in the investigated cases. The presented method fuses texture and geometry information by combining image, vertex and normal data to compute an illumination-invariant optical flow. By using a coarse-to-fine strategy, globally anchored optical flows are learned, reducing the impact of erroneous shading-based pseudo-correspondences. Based on the learned optical flows, a second architecture is proposed that predicts robust rigid transformations from the warped vertex and normal maps. Particular attention is payed to situations with strong rotations, which often cause such shading changes. Therefore a 3-step procedure is proposed that profitably exploits correlations between the normals and vertices. The method has been evaluated on a newly created dataset containing both synthetic and real data with strong rotations and shading effects. This data represents the typical use case in 3D reconstruction, where the object often rotates in large steps between the partial reconstructions. Additionally, we apply the method to the well-known Kitti Odometry dataset. Even if, due to fulfillment of the brighness assumption, this is not the typical use case of the method, the applicability to standard situations and the relation to other methods is therefore established.

READ FULL TEXT

page 5

page 6

page 10

page 12

page 13

page 14

page 15

page 17

research
12/08/2017

Dense Optical Flow based Change Detection Network Robust to Difference of Camera Viewpoints

This paper presents a novel method for detecting scene changes from a pa...
research
01/11/2023

Optical Flow for Autonomous Driving: Applications, Challenges and Improvements

Optical flow estimation is a well-studied topic for automated driving ap...
research
10/09/2020

Robust Isometric Non-Rigid Structure-from-Motion

Non-Rigid Structure-from-Motion (NRSfM) reconstructs a deformable 3D obj...
research
05/17/2018

Joint direct estimation of 3D geometry and 3D motion using spatio temporal gradients

Conventional image motion based structure from motion methods first comp...
research
06/29/2023

The Drunkard's Odometry: Estimating Camera Motion in Deforming Scenes

Estimating camera motion in deformable scenes poses a complex and open r...
research
12/20/2018

Robustness Meets Deep Learning: An End-to-End Hybrid Pipeline for Unsupervised Learning of Egomotion

In this work, we propose a method that combines unsupervised deep learni...
research
02/20/2020

Complete Endomorphisms in Computer Vision

Correspondences between k-tuples of points are key in multiple view geom...

Please sign up or login with your details

Forgot password? Click here to reset