The KITTI Vision Benchmark Suite之Displets: Stereo using Object Knowledge
来源:互联网 发布:双色球软件2016破解 编辑:程序博客网 时间:2024/06/04 19:29
Stereo techniques have witnessedtremendous巨大 progress over the last decades, yet some aspects of the problem still remain challenging today. Striking examples are reflecting and textureless surfaces which cannot easily be recovered using traditional localregularizers. In this work, we therefore propose to regularize over larger distances using object-category specific disparity proposals (displets) which we sample usinginverse graphics techniques based on a sparse disparity estimate and a semantic segmentation of the image. The proposed displets encode the fact that objects of certain categories are not arbitrarily shaped but typically exhibit regular structures. We integrate them as non-local regularizer for the challenging object class 'car' into a superpixel based CRF framework and demonstrate its benefits on the KITTI stereo evaluation. Our approach currently ranks first across all KITTI stereo leaderboards. The figure above depicts the result of our method on a challenging image. The left figure shows the input image with the inferred objectwireframe线框 modelsoverlayed覆盖. The right figure depicts the jointly inferred disparity map.
Introduction
Model
where i ~ j denotes the set of adjacent superpixels in S. In addition to the classic data term and pairwise constraints, we introduce long-range interactions into our model using displets: The displet unary potential (third term) encourages image regions with semantic class label c to be explained by a displet of the corresponding class. The last term ensures the displet and the associated superpixels in the image to be consistent.
Results
Below, we show three qualitative results in terms of theinferred推断 displets as well as the influence of the displets on the geometry of the superpixels. The influence is encoded as alpha channel: transparent 透明= no influence, solid = large influence.
Below, we visualize our results in terms ofinferred disparity maps推测差距图 on three different examples. Top-left: Input image, top-right: Semantic segments from ALE, bottom-left: input disparity map obtained viasemi-global matching (SGM), bottom-right: our result.
Videos
Changelog
- 18.05.2016: Updated code and data files to work with MC-CNN-accurate and to produce results on KITTI 2015.
- 28.08.2015: First version online!
Download
- Paper (pdf, 4 MB)
- Extended Abstract (pdf, 1 MB)
- Supplementary Material (pdf, 10 MB)
- Poster (pdf, 8 MB)
- Slides (pdf, 11 MB)
- Displets Code (Matlab/C++, 5 MB)
- Displets Data (3D Models/pre-processed data, required to run the displets demo, 3 GB)
- Semantic and instance labels for all cars in the KITTI stereo 2012 training set (optional, 1 MB)
- Semi-convex Hull Code for creating low-res motion models (optional)
Citation
@INPROCEEDINGS{Guney2015CVPR,
author = {Fatma Güney and Andreas Geiger},
title = {Displets: Resolving Stereo Ambiguities using Object Knowledge},
booktitle = {Conference on Computer Vision and Pattern Recognition (CVPR)},
year = {2015}
}
0 0
- The KITTI Vision Benchmark Suite之Displets: Stereo using Object Knowledge
- The KITTI Vision Benchmark Suite之Stereo Evaluation 2012
- The KITTI Vision Benchmark Suite之Stereo Evaluation 2015
- The KITTI Vision Benchmark Suite之Sensor Setup篇章
- Welcome to the KITTI Vision Benchmark Suite!
- The KITTI Vision Benchmark Suite之Semi-Convex Hull for Mesh Simplification
- [Paper]Resolving Stereo Ambiguities using Object Knowledge(未完成)
- Stereo Vision 常用网站
- Stereo Vision 常用网站
- Postprocessing of stereo vision
- stereo vision 领域一些期刊
- 学习笔记:MySQL基准测试之Benchmark Suite
- [论文解读] 3DOP: 3D Object Proposals using Stereo Imagery for Accurate Object Class Detection
- Stereo Matching文献笔记之(四):《Stereo Matching Using Tree Filtering》读后感~
- Stereo Matching文献笔记之(四):《Stereo Matching Using Tree Filtering》读后感~
- Benchmark Code on DSP using the Time Stamp Counter (TSC)
- Using the Meta Object Compiler
- Java Grande benchmark suite总结
- hbase的hbase-env.sh脚本修改的部分高亮显示(兰色添加,紫色注释)
- evpp设计细节系列(1):利用 enable_shared_from_this 实现一个自管理的定时器
- 第3章 运算符 选择结构
- POJ 1661 Help Jimmy (DP)
- Codeforces Round #277.5(Div. 2) C. Given Length and Sum of Digits...【贪心】
- The KITTI Vision Benchmark Suite之Displets: Stereo using Object Knowledge
- TreeMap集合特点、排序原理
- BZOJ1016: [JSOI2008]最小生成树计数
- linux静态库
- javascript编写活动倒计时
- ZOJ-1094-Matrix Chain Multiplication
- unit15 系统虚拟机管理
- LeakCanary用法(内存泄漏检查)
- 【HTML】表格样式