作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程

• •    

基于空间传播的多视图三维重建

  • 发布日期:2023-11-14

Spatial Propagation-based Multi-view 3D Reconstruction

  • Published:2023-11-14

摘要: [1] GALLIANI S, LASINGER K, SCHINDLERK. Massi- vely parallel multi view stereopsis by surface normal diffusion[C]//Proceedings of the IEEE International C -onference on Computer Vision. Boston, USA: IEEE P -ress, 2015: 873-881.
[2] XU Q, KONG W, TAO W, et al. Multi-Scale Geom- etric Consistency Guided and Planar Prior Assisted Multi View Stereo[J]. IEEE Transactions on Patt- ern Analysis and Machine Intelligence, 2022, 16(3):3 6-45.
[3] 尹晨阳,职恒辉,李慧斌. 基于深度学习的双目立体匹 配方法综述[J]. 计算机工程,2022,48(10):1-12.YIN C Y,ZHI H H,LI H B. Survey of binocular s-tereo- matching methods based on deep learning[J]. C-ompu ter Engineering,2022,48(10):1-12. (in Chine-se)
[4] YAO Y, LUO Z, LI S, et al. Mvsnet: Depth infere- nce for unstructured multi-view stereo[C]//Proceedin- gs ofthe European conference on computer vision (E- CCV). Salt Lake City, USA: IEEE Press, 2018: 767- 783.
[5] GU X, FAN Z, ZHU S, et al. Cascade cost volume for high-resolution multi-view stereo and stereo matc- hing[C]//Proceedings of the IEEE/CVF conference on computer vision and pattern recognition. Washington D.C. , USA: IEEE Press, 2020: 2495-2504.
[6] 刘会杰,柏正尧,程威,李俊杰,许祝. 融合注意力机 制和多层 U-Net 的多视图立体重建[J]. 中国图象图形 学报,2022,27(02):0475-0485.LIU H J,BAI Z Y, CHENG W,et al. Fusion atte-ntion mechanism and multilayer U-Net for multiviewstereo. Journal of Ima ge and Graphics,2022,27(02):0475-0485. (in Chin ese)
[7] YANG J, MAO W, ALVAREZ J M, et al. Cost volu -me pyramid based depth inference for multi-view ste -reo[C]//Proceedings of the IEEE/CVF Conferenceon C -omputer Vision and Pattern Recognition. Washington D.C.,USA: IEEE Press, 2020: 4877-4886.
[8] GAO S, LI Z, WANG Z. Cost Volume Pyramid Net- work with Multi-strategies Range Searching for Multi -view Stereo[J].Springer, 2022, 10(2): 157-169.
[9] CHENG S, XU Z, ZHU S, et al. Deep stereo using adaptive thin volume representation with uncertainty a- wareness[C]//Proceedings of the IEEE/CVF Conferenc- e on Computer Vision and Pattern Recognition. Was- hington D.C. , USA: IEEE Press, 2020: 2524-2534.
[10] 李剑,陈宇航. 一种多视角高精度图片的深度估计方法 [J]. 北京邮电大学学报(自科版),2021,44(5):101-10 6.LI J,CHEN Y H.A depth estimation method for m u-lti view and high precision images[J]. Journal of B ei-jing University of Posts and Telecommunications,2 021, 44(5):101-106. (in Chinese)
[11] CAO C, REN X, FU Y. MVSFormer: Multi-View St- ereo with Pre-trained Vision Transformers and Tempe- rature-based Depth[EB/OL]. [2022-12-16]. https://arxiv. org/abs/2208. 02541.
[12] LUO X., XIE, Y. FFP-MVSNet: Feature Fusion Base -d Patchmatch for Multi-view Stereo[C]//Communicati- ons Signal Processing and Systems. Berlin, Germany: Springer, 2022: 167-173
[13] YU Z, GAO S. Fast-mvsnet: Sparse-to-dense multi-vi- ew stereo with learned propagation and gauss-newton refinement[C]//Proceedings of the IEEE/CVF Confere- nceon Computer Vision and Pattern Recognition. Wa-shington D.C. , USA: IEEE Press, 2020: 1949-1958.
[14] PENG R, WANG R, WANG Z, et al. Rethinking De -pth Estimation for Multi-View Stereo: A Unified Re p-resentation. Proceedings of the IEEE/CVF Conferen c-e on Computer Vision and Pattern Recogni-tion. Ne wOrleans, USA: IEEE Press, 2022: 8635-8644.
[15] YAO Y, LUO Z, LI S, et al. Recurrent mvsnet for h -igh-resolution multi-view stereo depth inference[C]//P -roceedings of the IEEE/CVF conference on compute rvision and pattern recognition. Long Beach, USA: I E-EE Press, 2019: 5525-5534.
[16] YANG J, ALVAREZ J M, LIU M. Non-parametric D- epth Distribution Modelling based Depth Inference for Multi-view Stereo[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recogni- tion. New Orleans, USA: IEEE Press, 2022: 8626-86 34.
[17] 刘万军,王俊恺,曲海成. 多尺度代价体信息共享的多 视角立体重建网络[J]. 中国图象图形学报,2022,27(1 1):3331-3342. LIU W J,WANG J K,QU H C. Multi-scale cost v -olumes information sharing based multi-view stereo re -constructed model. Journal of Image and Graphics, 2 022,27(11):3331-3342. (in Chinese)
[18] BLEYER M, RHEMANN C, ROTHER C. Patchmatc- h stereo-stereo matching with slanted support windo- ws[C]//Proceedings of the British Machine Vision C- onference. Britain, UK: IEEE Press, 2011: 1-11.
[19] LI C, ZHOU A, YAO A. Omni-dimensional dynam- ic convolution[J]. Acta Optica Sinica, 2022, 1(2): 169 -181.
[20] CHENG X, WANG P, YANG R. Depth estimation v- ia affinity learned with convolutional spatial propagat- ion network[C]//Proceedings of the European Confere- nce on Computer Vision (ECCV). Munich, Germany: Springer Press, 2018: 103-119.
[21] AANAES H, JENSEN R R, VOGIATZIS G, et al. L- arge-scale data for multiple-view stereopsis[J]. Intern- ational Journal of Computer Vision, 2016, 120(5): 15 3-168.
[22] KNAPITSCH A, PARK J, ZHOU Q Y, et al. Tanks and temples: Benchmarking large-scale scene reconstr- uction[J]. ACM Transactions on Graphics (ToG) 2017, 36(4): 1-13.
[23] YAO Y, LUO Z, LI S, et al. Blendedmvs: A large-s- cale dataset for generalized multi-view stereo netwo- rks[C]//Proceedings of the IEEE/CVF Conference on C- omputer Vision and Pattern Recognition. Washington D.C. , USA: IEEE Press, 2020: 1790-1799.
[24] PASZKE A, GROSS S, CHINTALA S, et al. Autom- atic differentiation in pytorch[J]. Automatic different- iation in PyTorch, 2017, 8(2): 458-465.
[25] FURUKAWA Y, PONCE J. Accurate Dense and Ro- bust Multi-view Stereopsis[J]. Pattern Analysis and M- achine Intelligence, 2010, 32(8): 1362-1376.
[26] SCHONBERGER J L, FRAHM J M. Structure-from- motion revisited[C]//Proceedings of the IEEE confere- nce on computer vision and pattern recognition. Las Vegas, USA: IEEE Press, 2016: 4104-4113.
[27] YU A, GUO W, LIU B, et al. Attention aware cost volume pyramid based multi-view stereo network for 3d reconstruction[J]. ISPRS Journal of Photogrammet- ryand Remote Sensing, 2021, 175(6): 448-460.
[28] WANG F, GALLIANI S, VOGEL C, et al. Patch- matchnet: Learned multi-view patchmatch stereo[C]//P- roceedings of the IEEE/CVF Conference on Compute- r Vision and Pattern Recognition. Nashville, USA: I- EEE Press, 2021: 14194-14203.
[29] XU Q, OSWALD M R, TAO W, et al. Non-local re- current regularization networks for multi-view stereo [J]. IEEE Access, 2021, 6(8): 132586-132597.
[30] WEILHARTER R, FRAUNDORFER F. ATLAS-MVS Net: Attention Layers for Feature Extraction and Cost Volume Regularization in Multi-View Stereo[C]//2022 26th International Conference on Pattern Recognition (ICPR).New Orleans, USA: IEEE Press, 2022: 3557-3 563.
[31] MA X, GONG Y, WANG Q, et al. EPP-MVSNet: E- pipolar-assembling based depth prediction for multi-v- iewstereo[C]//Proceedings of the IEEE/CVF Internati- onal Conference on Computer Vision. Nashville, USA: IEEE Press, 2021: 5732-5740.
[32] WANG L, GONG Y, MA X, et al. IS-MVSNet: Imp- ortance Sampling-Based MVSNet[C]//Computer Vision ECCV 2022: 17th European Conference. Cham, Swit- zerland: Springer Press, 2022: 668-683.
[33] WANG F, GALLIANI S, VOGEL C, et al. IterMVS: iterative probability estimation for efficient multi-vie-wstereo[C]//Proceedings of the IEEE/CVF Conferen- ceon Computer Vision and Pattern Recognition. New Orleans, USA: IEEE Press, 2022: 8606-8615.
[34] XI J, SHI Y, WANG Y, et al. Raymvsnet:Learning ray-based 1d implicit fields for accurate multi-view s- tereo[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. New Orle- ans, USA: IEEE Press, 2022: 8595-8605.
[35] ZHANG X D, YANG F Z, CHANG M, et al. MG- MVSNet: Multiple granularities feature fusion network for multi-view stereo[J]. Neurocomputing, 2023, 528 (1): 35-47
[36] LUO K, GUAN T, JU L, et al. P-mvsnet: Learning patch-wise matching confidence aggregation for multi- view stereo[C]//Proceedings of the IEEE/CVF Interna- tional Conference on Computer Vision. Long Beach, USA: IEEE Press, 2019: 10452-10461.
[37] CHEN R, HAN S, XU J, et al. Visibility-aware poi- nt-based multi-view stereo network[J]. IEEE transact- ionson pattern analysis and machine intelligence, 202 0, 43(10): 3695-3708.