浏览全部资源
扫码关注微信
Received：17 October 2023，
Revised：2024-01-04，
Published：16 October 2024
移动端阅览
目的
2
全局式从运动恢复结构（structure from motion， SfM）通过运动平均一次性恢复所有相机的绝对位姿，效率相对较高。运动平均中的平移平均主要负责解算相机在世界坐标系下的绝对位置，其求解过程因尺度歧义性、估计敏感性和求解不确定性的影响而较为困难。本文提出了一种基于增量尺度估计的平移平均方法，在消除尺度歧义性的同时提升了求解鲁棒性与准确性。
方法
2
本文将平移平均问题解耦为3个子问题：1）局部绝对尺度的增量式估计；2）全局绝对尺度的增量式估计；3）基于
<math id="M1"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855888&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855890&type=
2.70933342
优化的尺度已知的绝对位置估计。
结果
2
在1DSfM数据集上进行对比实验，基线解算精度明显提升，解算相机百分比的均值达到96%。当引入两种不同的绝对旋转进行计算时，其绝对位置中值误差仅略差于BATA（bilinear angle-based translation averaging）与CReTA（correspondence reweighted translation averaging），排名第3，均值误差改善更为明显，分别排名第1和第2。相较于原始方法，本文方法在相机解算数量与位置解算精度上均有较大提升。
结论
2
本文方法综合了尺度分离思想与增量式参数估计思想，既消除了尺度歧义性，又保证了鲁棒性与高效性，求解所得的相机绝对位置稳定可靠。
Objective
2
The structure from motion （SfM） technique serves as the fundamental step in the sparse reconstruction process， finding extensive applications in remote sensing mapping， indoor modeling， augmented reality， and ancient architecture preservation. SfM technology retrieves camera poses from images， encompassing two main categories： incremental and global approaches. The global SfM， in contrast to the iterative nature of incremental SfM， simultaneously estimates the absolute poses of all cameras through motion averaging， resulting in relatively high efficiency. However， it still encounters challenges regarding robustness and accuracy. Rotation averaging and translation averaging constitute crucial components within the motion averaging. Compared with rota
tion averaging， translation averaging is more difficult due to the following three reasons： 1） Only relative translation directions could be recovered by essential matrix estimation and decomposition， i.e.， the produced relative translations are scale ambiguous. 2） Only cameras in the same parallel rigid component could their absolute locations be uniquely determined by translation averaging， while for rotation averaging， the requirement simply degenerates to the connected component. 3） Compared with relative rotation， the estimation accuracy of relative translation is more vulnerable to the feature point mismatches and more likely to be outlier contaminated. In traditional approaches， the translation averaging method based on scale separation （
<math id="M2"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855875&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855877&type=
6.34999990
-
<math id="M3"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">T</mi><mi mathvariant="normal">A</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855900&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855901&type=
6.85799980
） calculates the relative baseline length between cameras before estimating the absolute locations， eliminates the scale ambiguity， and the solving range is no longer constrained by the camera triplet， but its robustness and accuracy still need to be improved. Incremental translation averaging （ITA） introduces the idea of incremental parameter estimation into the translation averaging process for the first time， which has good robustness and high accuracy. However， its solving process depends on camera triplets and may suffer from degeneracy during collinear camera motion. To solve the above problems， this study proposes a translation averaging method based on incremental scale estimation （
<math id="M4"><mi mathvariant="normal">I</mi><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857939&type=
2.28600001
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857941&type=
4.57200003
-
<math id="M5"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">T</mi><mi mathvariant="normal">A</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857958&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857960&type=
6.85799980
）， which eliminates the scale ambiguity and enhances the method's robustness and result accuracy.
Method
2
Incremental SfM has been proven to be highly accurate and robust， making it a preferred choice for many applications. It has shown to be particularly effective in handling large datasets and overcoming the challenges posed by complex real-world scenarios. Recognizing its potential， researchers have sought to transfer the incremental parameter estimation ideology to other related tasks， such as incremental rotation averaging （IRA） and ITA. In particular， IRA is designed to estimate the camera absolute rotations incrementally and efficiently. Meanwhile， ITA is performed for the camera absolute locations， enabling it to handle outliers effectively and avoid error propagation. Overall， the adoption of incremental parameter estimation ideology for motion averaging tasks demonstrates the versatility and effectiveness of this approach. With its ability to handle complex datasets and overcome a range of challenges， the incremental parameter estimation ideology holds great promise for future research in the field of 3D reconstruction and beyond. In this study，
<math id="M6"><mi mathvariant="normal">I</mi><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857939&type=
2.28600001
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857941&type=
4.57200003
-
<math id="M7"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">T</mi><mi mathvariant="normal">A</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857958&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67857960&type=
6.85799980
is proposed by incorporating the scale separation strategy and incremental parameter estimation ideology. Specifically， the translation averaging problem is decomposed into three sub-ones and sequentially solved： 1） incremental estimation of local absolute scale， 2） incremental estimation of global absolute scale， 3） scale-aware absolute location estimation based on
<math id="M8"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855888&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855890&type=
2.70933342
optimization. The input of our proposed method is the pairwise scale invariant feature transform point matches， and its output is the absolute camera locations. First， the relative motion between cameras is obtained by estimating and decomposing the essential matrix. Next， the two-view triangulation is performed to calculate the relative depths in the local coordinate system. On the basis of depth ratios， incremental estimations are conducted for the local and global absolute scales. Subsequently， the relative baseline length between cameras is computed， and rotation averaging is performed for abs
olute rotation estimation， enabling the final scale-aware absolute location estimation.
Result
2
We performed experimental tests to evaluate the selection of scale distance function and scale distance threshold. The experimental results confirmed that the normalized perfect square deviation function effectively eliminates the impact of scaling effects. Furthermore， the incremental scale estimation method shows good robustness and insensitivity to scale distance threshold and achieves remarkably higher baseline accuracy compared with
<math id="M9"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855872&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855903&type=
6.34999990
. The experiments were conducted on the 1DSfM dataset. In comparison with various state-of-the-art methods including bilinear angle-based translation averaging （BATA）， correspondence reweighted translation averaging （CReTA）， ITA， and
<math id="M10"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855904&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855905&type=
6.34999990
-
<math id="M11"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">T</mi><mi mathvariant="normal">A</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855900&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855901&type=
6.85799980
， our proposed method exhibited the following performance： 1） In terms of the number of cameras solved， the average percentage of successfully solved cameras using the proposed method is 96%. 2） The median error of absolute location estimation is slightly worse than that of BATA and CReTA and ranks third overall under different absolute rotations. 3） In terms of the mean error in absolute location estimation， the proposed method has remarkable advantages， ranking first and second respectively. Compared with the original
<math id="M12"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">S</mi><mi mathvariant="normal">E</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855908&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855899&type=
6.34999990
-
<math id="M13"><msub><mrow><mi>L</mi></mrow><mrow><mn mathvariant="normal">1</mn></mrow></msub><mi mathvariant="normal">T</mi><mi mathvariant="normal">A</mi></math>
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855900&type=
3.21733332
https://html.publish.founderss.cn/rc-pub/api/common/picture?pictureId=67855901&type=
6.85799980
， the method in this study has a great improvement in the number of cameras solved and the accuracy of locations estimated.
Conclusion
2
The proposed method combines the concept of scale separation with incremental parameter estimation. By integrating these two ideas， our method effectively eliminates scale ambiguity while ensuring the effectiveness of outlier rejection and maintaining a concise solving process. As a result， the obtained absolute camera locations are stable and reliable.
Bourmaud G . 2016 . Online variational Bayesian motion averaging // Proceedings of the 14th European Conference on Computer Vision . Amsterdam， the Netherlands ： Springer： 126 - 142 ［ DOI： 10.1007/978-3-319-46484-8_8 http://dx.doi.org/10.1007/978-3-319-46484-8_8 ］
Candès E J ， Wakin M B and Boyd S P . 2008 . Enhancing sparsity by reweighted ℓ 1 minimization . Journal of Fourier Analysis and Applications ， 14 （ 5/6 ）： 877 - 905 ［ DOI： 10.1007/s00041-008-9045-x http://dx.doi.org/10.1007/s00041-008-9045-x ］
Chatterjee A and Govindu V M . 2013 . Efficient and robust large-scale rotation averaging // Proceedings of 2013 IEEE International Conference on Computer Vision . Sydney， Australia ： IEEE： 521 - 528 ［ DOI： 10.1109/ICCV.2013.70 http://dx.doi.org/10.1109/ICCV.2013.70 ］
Cui H N ， Shen S H ， Gao X and Hu Z Y . 2017 . Batched incremental structure-from-motion // Proceedings of 2017 IEEE International Conference on 3D Vision . Qingdao， China ： IEEE： 205 - 214 ［ DOI： 10.1109/3DV.2017.00032 http://dx.doi.org/10.1109/3DV.2017.00032 ］
Cui Z P and Tan P . 2015 . Global structure-from-motion by similarity averaging // Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago， Chile ： IEEE： 864 - 872 ［ DOI： 10.1109/ICCV.2015.105 http://dx.doi.org/10.1109/ICCV.2015.105 ］
Furukawa Y and Ponce J . 2010 . Accurate， dense， and robust multiview stereopsis . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 32 （ 8 ）： 1362 - 1376 ［ DOI： 10.1109/TPAMI.2009.161 http://dx.doi.org/10.1109/TPAMI.2009.161 ］
Gao X ， Luo J Z ， Li K Q and Xie Z X . 2020 . Hierarchical RANSAC-based rotation averaging . IEEE Signal Processing Letters ， 27 ： 1874 - 1878 ［ DOI： 10.1109/LSP.2020.3031759 http://dx.doi.org/10.1109/LSP.2020.3031759 ］
Gao X ， Zhu L J ， Cui H N ， Xie Z X and Shen S H . 2022a . IRA++： distributed incremental rotation averaging . IEEE Transactions on Circuits and Systems for Video Technology ， 32 （ 7 ）： 4885 - 4892 ［ DOI： 10.1109/TCSVT.2021.3118883 http://dx.doi.org/10.1109/TCSVT.2021.3118883 ］
Gao X ， Zhu L J ， Fan B ， Liu H M and Shen S H . 2022b . Incremental translation averaging . IEEE Transactions on Circuits and Systems for Video Technology ， 32 （ 11 ）： 7783 - 7795 ［ DOI： 10.1109/TCSVT.2022.3183631 http://dx.doi.org/10.1109/TCSVT.2022.3183631 ］
Gao X ， Zhu L J ， Xie Z X ， Liu H M and Shen S H . 2021 . Incremental rotation averaging . International Journal of Computer Vision ， 129 （ 4 ）： 1202 - 1216 ［ DOI： 10.1007/s11263-020-01427-7 http://dx.doi.org/10.1007/s11263-020-01427-7 ］
Gao X ， Cui H N ， Huang W T ， Li M H and Shen S H . 2024 . IRAv3+： hierarchical incremental rotation averaging via multiple connected dominating sets . IEEE Transactions on Circuits and Systems for Video Technology ， 34 （ 4 ）： 3049 - 3055 ［ DOI： 10.1109/TCSVT.2023.3309661 http://dx.doi.org/10.1109/TCSVT.2023.3309661 ］
Gao X ， Cui H N ， Li M H ， Xie Z X and Shen S H . 2023a . IRAv3： hierarchical incremental rotation averaging on the fly . IEEE Transactions on Circuits and Systems for Video Technology ， 33 （ 4 ）： 2001 - 2006 ［ DOI： 10.1109/TCSVT.2022.3217151 http://dx.doi.org/10.1109/TCSVT.2022.3217151 ］
Gao X ， Cui H N and Shen S H . 2023b . Incremental rotation averaging revisited and more： a new rotation averaging benchmark ［EB/OL］. ［ 2023-09-29 ］. https://arxiv.orgpdf/2309.16924.pdf https://arxiv.orgpdf/2309.16924.pdf
Goldstein T ， Hand P ， Lee C ， Voroninski V and Soatto S . 2016 . ShapeFit and ShapeKick for robust， scalable structure from motion // Proceedings of the 14th European Conference on Computer Vision-ECCV 2016 . Amsterdam， the Netherlands ： Springer： 289 - 304 ［ DOI： 10.1007/978-3-319-46478-7_18 http://dx.doi.org/10.1007/978-3-319-46478-7_18 ］
Govindu V M . 2001 . Combining two-view constraints for motion estimation // Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Kauai， USA ： IEEE： 218 - 225 ［ DOI： 10.1109/CVPR.2001.990963 http://dx.doi.org/10.1109/CVPR.2001.990963 ］
Govindu V M . 2004 . Lie-algebraic averaging for globally consistent motion estimation // Proceedings of 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition . Washington， USA ： IEEE： #1 ［ DOI： 10.1109/CVPR.2004.1315098 http://dx.doi.org/10.1109/CVPR.2004.1315098 ］
Govindu V M . 2006 . Robustness in motion averaging // Proceedings of the 7th Asian Conference on Computer Vision-ACCV 2006 . Hyderabad， India ： Springer： 457 - 466 ［ DOI： 10.1007/11612704_46 http://dx.doi.org/10.1007/11612704_46 ］
Govindu V M and Pooja A . 2014 . On averaging Multiview relations for 3D scan registration . IEEE Transactions on Image Processing ， 23 （ 3 ）： 1289 - 1302 ［ DOI： 10.1109/TIP.2013.2246517 http://dx.doi.org/10.1109/TIP.2013.2246517 ］
Kasten Y ， Geifman A ， Galun M and Basri R . 2019 . Algebraic Characterization of Essential Matrices and Their Averaging in Multiview Settings // Proceedings of 2019 IEEE International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 5894 - 5902 ［ DOI： 10.1109/ICCV.2019.00599 http://dx.doi.org/10.1109/ICCV.2019.00599 ］
Hartley R I and Sturm P . 1997 . Triangulation . Computer Vision and Image Understanding ， 68 （ 2 ）： 146 - 157 ［ DOI： 10.1006/cviu.1997.0547 http://dx.doi.org/10.1006/cviu.1997.0547 ］
Jancosek M and Pajdla T . 2011 . Multi-view reconstruction preserving weakly-supported surfaces // Proceedings of 2011 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Colorado Springs， USA ： IEEE： 1362 - 1376 ［ DOI： 10.1109/cvpr.2011.5995693 http://dx.doi.org/10.1109/cvpr.2011.5995693 ］
Jiang N J ， Cui Z P and Tan P . 2013 . A global linear method for camera pose registration // Proceedings of 2013 IEEE International Conference on Computer Vision . Sydney， Australia ： IEEE： 481 - 488 ［ DOI： 10.1109/ICCV.2013.66 http://dx.doi.org/10.1109/ICCV.2013.66 ］
Lee S H and Civera J . 2019 . Closed-form optimal two-view triangulation based on angular errors // Proceedings of 2019 IEEE/CVF International Conference on Computer Vision . Seoul， Korea （South） ： IEEE： 2681 - 2689 ［ DOI： 10.1109/ICCV.2019.00277 http://dx.doi.org/10.1109/ICCV.2019.00277 ］
Lee S H and Civera J . 2022 . HARA： a hierarchical approach for robust rotation averaging // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， USA ： IEEE： 15777 - 15786 ［ DOI： 10.1109/CVPR52688.2022.01532 http://dx.doi.org/10.1109/CVPR52688.2022.01532 ］
Li H ， Cui Z P ， Liu S C and Tan P . 2022 . RAGO： recurrent graph optimizer for multiple rotation averaging // Proceedings of 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition . New Orleans， USA ： IEEE： 15787 - 15796 ［ DOI： 10.1109/CVPR52688.2022.01533 http://dx.doi.org/10.1109/CVPR52688.2022.01533 ］
Lowe D G . 2004 . Distinctive image features from scale-invariant keypoints . International Journal of Computer Vision ， 60 （ 2 ）： 91 - 110 ［ DOI： 10.1023/B：VISI.0000029664.99615.94 http://dx.doi.org/10.1023/B：VISI.0000029664.99615.94 ］
Manam L and Govindu V M . 2022 . Correspondence reweighted translation averaging // Proceedings of the 17th European Conference on Computer Vision-ECCV 2022 . Tel Aviv， Israel ： Springer： 56 - 72 ［ DOI： 10.1007/978-3-031-19827-4_4 http://dx.doi.org/10.1007/978-3-031-19827-4_4 ］
Moulon P ， Monasse P and Marlet R . 2012 . Adaptive structure from motion with a Contrario model estimation // Proceedings of the 11th Asian Conference on Computer Vision . Daejeon， Korea （South） ： Springer： 257 - 270 ［ DOI： 10.1007/978-3-642-37447-0_20 http://dx.doi.org/10.1007/978-3-642-37447-0_20 ］
Moulon P ， Monasse P and Marlet R . 2013 . Global fusion of relative motions for robust， accurate and scalable structure from motion // Proceedings of 2013 IEEE International Conference on Computer Vision . Sydney， Australia ： IEEE： 3248 - 3255 ［ DOI： 10.1109/ICCV.2013.403 http://dx.doi.org/10.1109/ICCV.2013.403 ］
Muja M and Lowe D G . 2014 . Scalable nearest neighbor algorithms for high dimensional data . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 36 （ 11 ）： 2227 - 2240 ［ DOI： 10.1109/TPAMI.2014.2321376 http://dx.doi.org/10.1109/TPAMI.2014.2321376 ］
Ning X J ， Gong L ， Han Y ， Ma T ， Shi Z H ， Jin H Y and Wang Y H . 2023 . Semantic segmentation and model matching-integrated indoor scenario-relevant reconstruction method . Journal of Image and Graphics ， 28 （ 10 ）： 3149 - 3162
宁小娟 ， 巩亮 ， 韩怡 ， 马婷 ， 石争浩 ， 金海燕 ， 王映辉 . 2023 . 结合语义分割与模型匹配的室内场景重建方法 . 中国图象图形学报 ， 28 （ 10 ）： 3149 - 3162 ［ DOI： 10.11834/jig.220518 http://dx.doi.org/10.11834/jig.220518 ］
Nister D . 2004 . An efficient solution to the five-point relative pose problem . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 26 （ 6 ）： 756 - 770 ［ DOI： 10.1109/TPAMI.2004.17 http://dx.doi.org/10.1109/TPAMI.2004.17 ］
Özyeşil O and Singer A . 2015 . Robust camera location estimation by convex programming // Proceedings of 2015 IEEE Conference on Computer Vision and Pattern Recognition . Boston， USA ： IEEE： 2674 - 2683 ［ DOI： 10.1109/CVPR.2015.7298883 http://dx.doi.org/10.1109/CVPR.2015.7298883 ］
Purkait P ， Chin T J and Reid I . 2020 . NeuRoRA： neural robust rotation averaging // Proceedings of the 16th European Conference on Computer Vision-ECCV 2020 . Glasgow， UK ： Springer： 137 - 154 ［ DOI： 10.1007/978-3-030-58586-0_9 http://dx.doi.org/10.1007/978-3-030-58586-0_9 ］
Ren F E ， Liu T and Yang L . 2021 . 3D reconstruction of a single plant leaf image . Journal of Image and Graphics ， 26 （ 11 ）： 2713 - 2722
任非儿 ， 刘通 ， 杨龙 . 2021 . 单幅植物叶片图像的3维重建 . 中国图象图形学报 ， 26 （ 11 ）： 2713 - 2722 ［ DOI： 10.11834/jig.200475 http://dx.doi.org/10.11834/jig.200475 ］
Schönberger J L and Frahm J M . 2016 . Structure-from-motion revisited // Proceedings of 2016 IEEE Conference on Computer Vision and Pattern Recognition . Las Vegas， USA ： IEEE： 4104 - 4113 ［ DOI： 10.1109/CVPR.2016.445 http://dx.doi.org/10.1109/CVPR.2016.445 ］
Shah R ， Deshpande A and Narayanan P J . 2014 . Multistage SFM： revisiting incremental structure from motion // Proceedings of the 2nd International Conference on 3D Vision . Tokyo， Japan ： IEEE： 417 - 424 ［ DOI： 10.1109/3DV.2014.95 http://dx.doi.org/10.1109/3DV.2014.95 ］
Shi Y P ， Wyeth C and Lerman G . 2022 . Robust group synchronization via quadratic programming // Proceedings of 2022 International Conference on Machine Learning . Beijing， China ： ICML： 20095 - 20105
Snavely N ， Seitz S M and Szeliski R . 2006 . Photo tourism： exploring photo collections in 3 D. ACM Transactions on Graphics ， 25 （ 3 ）： 835 - 846 ［ DOI： 10.1145/1141911.1141964 http://dx.doi.org/10.1145/1141911.1141964 ］
Snavely N ， Seitz S M and Szeliski R . 2008 . Modeling the world from Internet photo collections . International Journal of Computer Vision ， 80 （ 2 ）： 189 - 210 ［ DOI： 10.1007/s11263-007-0107-3 http://dx.doi.org/10.1007/s11263-007-0107-3 ］
Sweeney C ， Sattler T ， Höllerer T ， Turk M and Pollefeys M . 2015 . Optimizing the viewing graph for structure-from-motion // Proceedings of 2015 IEEE International Conference on Computer Vision . Santiago， Chile ： IEEE： 801 - 809 ［ DOI： 10.1109/ICCV.2015.98 http://dx.doi.org/10.1109/ICCV.2015.98 ］
Waechter M ， Moehrle N and Goesele M . 2014 . Let there be color！ large-scale texturing of 3D Reconstructions // Proceedings of the 13th European Conference on Computer Vision . Zürich， Switzerland ： Springer： 836 - 850 ［ DOI： 10.1007/978-3-319-10602-1_54 http://dx.doi.org/10.1007/978-3-319-10602-1_54 ］
Wang K Y ， Huang S R and Li Y S . 2022 . An optical reconstruction based underwater image analysis . Journal of Image and Graphics ， 27 （ 5 ）： 1337 - 1358
王柯俨 ， 黄诗芮 ， 李云松 . 2022 . 水下光学图像重建方法研究进展 . 中国图象图形学报 ， 27 （ 5 ）： 1337 - 1358 ［ DOI： 10.11834/jig.210819 http://dx.doi.org/10.11834/jig.210819 ］
Wilson K and Snavely N . 2014 . Robust global translations with 1DSfM // Proceedings of the 13th European Conference on Computer Vision . Zürich， Switzerland ： Springer： 61 - 75 ［ DOI： 10.1007/978-3-319-10578-9_5 http://dx.doi.org/10.1007/978-3-319-10578-9_5 ］
Wu C C . 2013 . Towards linear-time incremental structure from motion // Proceedings of 2013 IEEE International Conference on 3D Vision . Seattle， USA ： IEEE： 127 - 134 ［ DOI： 10.1109/3DV.2013.25 http://dx.doi.org/10.1109/3DV.2013.25 ］
Yan S ， Zhang M J ， Fan Y C ， Tan X H ， Liu Y ， Peng Y and Liu Y X . 2021 . Progress in the large-scale outdoor image 3D reconstruction . Journal of Image and Graphics ， 26 （ 6 ）： 1429 - 1449
颜深 ， 张茂军 ， 樊亚春 ， 谭小慧 ， 刘煜 ， 彭杨 ， 刘宇翔 . 2021 . 大规模室外图像3维重建技术研究进展 . 中国图象图形学报 ， 26 （ 6 ）： 1429 - 1449 ［ DOI： 10.11834/jig.200842 http://dx.doi.org/10.11834/jig.200842 ］
Yao L ， Zhang Y A ， Zhang M X and Wan Y . 2021 . The impact of joint axis angle prior on the results of 3D human body reconstruction . Journal of Image and Graphics ， 26 （ 12 ）： 2918 - 2930
姚砺 ， 张幼安 ， 张梦雪 ， 万燕 . 2021 . 关节轴角先验对3维人体重建结果的影响 . 中国图象图形学报 ， 26 （ 12 ）： 2918 - 2930 ［ DOI： 10.11834/jig.200348 http://dx.doi.org/10.11834/jig.200348 ］
Zhang G L ， Larsson V and Barath D . 2023 . Revisiting rotation averaging： uncertainties and robust losses // Proceedings of 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Vancouver， Canada ： IEEE： 17215 - 17224 ［ DOI： 10.1109/CVPR52729.2023.01651 http://dx.doi.org/10.1109/CVPR52729.2023.01651 ］
Zhao J . 2022 . An efficient solution to non-minimal case essential matrix estimation . IEEE Transactions on Pattern Analysis and Machine Intelligence ， 44 （ 4 ）： 1777 - 1792 ［ DOI： 10.1109/TPAMI.2020.3030161 http://dx.doi.org/10.1109/TPAMI.2020.3030161 ］
Zhu S Y ， Zhang R Z ， Zhou L ， Shen T W ， Fang T ， Tan P and Quan L . 2018 . Very large-scale global SfM by distributed motion averaging // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 4568 - 4577 ［ DOI： 10.1109/CVPR.2018.00480 http://dx.doi.org/10.1109/CVPR.2018.00480 ］
Zhuang B B ， Cheong L F and Lee G H . 2018 . Baseline desensitizing in translation averaging // Proceedings of 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition . Salt Lake City， USA ： IEEE： 4539 - 4547 ［ DOI： 10.1109/CVPR.2018.00477 http://dx.doi.org/10.1109/CVPR.2018.00477 ］
相关文章
相关作者
相关机构
京公网安备11010802024621
