资源论文Dense Semi-rigid Scene Flow Estimation from RGBD Images *

Dense Semi-rigid Scene Flow Estimation from RGBD Images *

2020-04-06 | |  61 |   39 |   0

Abstract

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 local and piece- wise rigidity of real world scenes. By modeling the motion as a field of twists, our method encourages piecewise smooth solutions of rigid body motions. We give a general formulation to solve for local and global rigid motions by jointly using intensity and depth data. In order to deal effi- ciently with a moving camera, we model the motion as a rigid component plus a non-rigid residual and propose an alternating solver. The evalu- ation demonstrates that the proposed method achieves the best results in the most commonly used scene flow benchmark. Through additional experiments we indicate the general applicability of our approach in a variety of different scenarios.

上一篇:Soft Cost Aggregation with Multi-resolution Fusion

下一篇:Learning Rich Features from RGB-D Images for Ob ject Detection and Segmentation

用户评价
全部评价

热门资源

  • The Variational S...

    Unlike traditional images which do not offer in...

  • Learning to Predi...

    Much of model-based reinforcement learning invo...

  • Stratified Strate...

    In this paper we introduce Stratified Strategy ...

  • A Mathematical Mo...

    Direct democracy, where each voter casts one vo...

  • Rating-Boosted La...

    The performance of a recommendation system reli...