Abstract
As a long-standing ill-posed problem, 3D reconstruction from a single image is an important research topic in computer vision. The information in a single image can represent an infinite number of possible three-dimensional shapes. To recover reasonable object geometry from a single image requires a correct shape prior. Thus, using what kind of supervision and how to make better use of training data are key issues. In this paper, we propose a framework for 3D reconstruction from single image with video supervision. On the one hand, we build a temporal network to generate fine 3D structure from video input benefiting from its temporal correlation. On the other hand, we introduce the knowledge distillation to transfer the shape prior extracted from the video. Also the mechanism ensures that the student network which for single image reconstruction can make full use of the knowledge learned from the teacher network which receives video input. In the inference phase, we can use the student network independently. Extensive experiments on ShapeNet show the superiority of our method.
Similar content being viewed by others
References
Barron JT, Malik J (2015) Shape, illumination, and reflectance from shading. IEEE Trans Pattern Anal Mach Intell 37(8):1670–1687
Broadhurst A, Drummond T, Cipolla R (2001) A probabilistic framework for space carving. In: ICCV, pp 388–393. IEEE Computer Society
Brown M, Lowe DG (2005) Unsupervised 3d object recognition and reconstruction in unordered datasets. In: 3DIM, pp 56–63. IEEE Computer Society
Cadena C, Carlone L, Carrillo H, Latif Y, Scaramuzza D, Neira J, Reid I, Leonard JJ (2016) Past, present, and future of simultaneous localization and mapping: toward the robust-perception age. IEEE Trans Robot 32 (6):1309–1332
Chang AX, Funkhouser TA, Guibas LJ, Hanrahan P, Huang Q, Li Z, Savarese S, Savva M, Song S, Su H, Xiao J, Yi L, Yu F (2015) Shapenet: an information-rich 3d model repository. arXiv:1512.03012
Choy CB, Xu D, Gwak J, Chen K, Savarese S (2016) 3d-r2n2: a unified approach for single and multi-view 3d object reconstruction. In: ECCV (8), Lecture notes in computer science, vol 9912, pp 628–644. Springer
Curless B, Levoy M (1996) A volumetric method for building complex models from range images. In: SIGGRAPH, pp 303–312. ACM
Dibra E, Jain H, Ȯztireli A C, Ziegler R, Gross MH (2017) Human shape from silhouettes using generative HKS descriptors and cross-modal neural networks. In: CVPR, pp 5504–5514. IEEE Computer Society
Fan H, Su H, Guibas LJ (2017) A point set generation network for 3d object reconstruction from a single image. In: CVPR, pp 2463–2471. IEEE Computer Society
Gadelha M, Maji S, Wang R (2017) 3d shape induction from 2d views of multiple objects. In: 3DV, pp 402–411. IEEE Computer Society
Glorot X, Bordes A, Bengio Y (2011) Deep sparse rectifier neural networks. In: AISTATS, JMLR Proceedings, vol 15, pp 315–323. JMLR.org
Goodfellow IJ, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville AC, Bengio Y (2014) Generative adversarial nets. In: NIPS, pp 2672–2680
Gou J, Yu B, Maybank SJ, Tao D (2021) Knowledge distillation: a survey. Int J Comput Vis 129(6):1789–1819
Gwak J, Choy CB, Chandraker M, Garg A, Savarese S (2017) Weakly supervised 3d reconstruction with adversarial constraint. In: 3DV, pp 263–272. IEEE Computer Society
Han X, Laga H, Bennamoun M (2021) Image-based 3d object reconstruction: state-of-the-art and trends in the deep learning era. IEEE Trans Pattern Anal Mach Intell 43(5):1578–1604
Harltey A, Zisserman A (2006) Multiple view geometry in computer vision, 2 edn. Cambridge University Press
He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: CVPR, pp 770–778. IEEE
Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780
Huang P, Matzen K, Kopf J, Ahuja N, Huang J (2018) Deepmvs: learning multi-view stereopsis. In: CVPR, pp 2821–2830. IEEE Computer Society
Insafutdinov E, Dosovitskiy A (2018) Unsupervised learning of shape and pose with differentiable point clouds. In: NeurIPS, pp 2807–2817
Ioffe S, Szegedy C (2015) Batch normalization: Accelerating deep network training by reducing internal covariate shift. In: ICML(2015), vol. 37, pp 448–456. JMLR.org
Kar A, Häne C, Malik J (2017) Learning a multi-view stereo machine. In: NIPS, pp 365–376
Kato H, Harada T (2019) Learning view priors for single-view 3d reconstruction. In: CVPR, pp 9778–9787. computer vision foundation / IEEE
Kato H, Ushiku Y, Harada T (2018) Neural 3d mesh renderer. In: CVPR, pp 3907–3916. IEEE Computer Society
Khodatars M, Shoeibi A, Sadeghi D, Ghaasemi N, Jafari M, Moridian P, Khadem A, Alizadehsani R, Zare A, Kong Y, Khosravi A, Nahavandi S, Hussain S, Acharya UR, Berk M (2021) Deep learning for neuroimaging-based diagnosis and rehabilitation of autism spectrum disorder: a review Computers in Biology and Medicine
Kingma DP, Ba J (2015) Adam: a method for stochastic optimization. In: ICLR (Poster)
Kingma DP, Welling M (2014) Auto-encoding variational bayes. In: ICLR
Laurentini A (1994) The visual hull concept for silhouette-based image understanding. IEEE Trans Pattern Anal Mach Intell 16(2):150–162
Liao X, Li K, Zhu X, Liu KJR (2020) Robust detection of image operator chain with two-stream convolutional neural network. IEEE Journal of Selected Topics in Signal Processing. https://doi.org/10.1109/JSTSP.2020.3002391
Liao X, Yin J, Chen M, Qin Z (2020) Adaptive payload distribution in multiple images steganography based on image texture features. IEEE Transactions on Dependable and Secure Computing. https://doi.org/10.1109/TDSC.2020.3004708
Liao X, Yu Y, Li B, Li Z, Qin Z (2020) A new payload partition strategy in color image steganography. IEEE Transactions on Circuits and Systems for Video Technology. https://doi.org/10.1109/TCSVT.2019.2896270
Lin C, Kong C, Lucey S (2018) Learning efficient point cloud generation for dense 3d object reconstruction. In: AAAI, pp 7114–7121. AAAI Press
Lin C, Wang O, Russell BC, Shechtman E, Kim VG, Fisher M, Lucey S (2019) Photometric mesh optimization for video-aligned 3d object reconstruction. In: CVPR, pp 969–978. Computer Vision Foundation / IEEE
Mandikal P, L NK, Agarwal M, Radhakrishnan VB (2018) 3d-lmnet: latent embedding matching for accurate and diverse 3d point cloud reconstruction from a single image. In: BMVC, p. 55. BMVA Press
Mandikal P, Radhakrishnan VB (2019) Dense 3d point cloud reconstruction using a deep pyramid network. In: WACV, pp 1052–1060. IEEE
Mo K, Guerrero P, Yi L, Su H, Wonka P, Mitra NJ, Guibas LJ (2019) Structurenet: hierarchical graph networks for 3d shape generation. ACM Trans Graph 38(6):242,1–242,19
Mo K, Zhu S, Chang AX, Yi L, Tripathi S, Guibas LJ, Su H (2019) Partnet: a large-scale benchmark for fine-grained and hierarchical part-level 3d object understanding. In: CVPR, pp 909–918. computer vision foundation / IEEE
Ning X, Duan P, Li W, Zhang S (2020) Real-time 3d face alignment using an encoder-decoder network with an efficient deconvolution layer. IEEE Signal Processing Letters
Paschalidou D, Gool LV, Geiger A (2020) Learning unsupervised hierarchical part decomposition of 3d objects from a single RGB image. In: CVPR, pp 1057–1067. IEEE
Paschalidou D, Ulusoy AO, Schmitt C, Gool LV, Geiger A (2018) Raynet: learning volumetric 3d reconstruction with ray potentials. In: CVPR, pp 3897–3906. IEEE computer society
Qi S, Ning X, Yang G, Zhang L, Long P, Cai W, Li W (2021) Review of multi-view 3d object recognition methods based on deep learning. Displays
Rezende DJ, Eslami SMA, Mohamed S, Battaglia PW, Jaderberg M, Heess N (2016) Unsupervised learning of 3d structure from images. In: NIPS, pp 4997–5005
Richter SR, Roth S (2015) Discriminative shape from shading in uncalibrated illumination. In: CVPR, pp 1128–1136. IEEE Computer Society
Richter SR, Roth S (2018) Matryoshka networks: Predicting 3d geometry via nested shape layers. In: CVPR, pp 1936–1944. IEEE Computer Society
Romero A, Ballas N, Kahou SE, Chassang A, Gatta C, Bengio Y (2015) Fitnets: hints for thin deep nets. In: ICLR (Poster)
Shoeibi A, Khodatars M, Alizadehsani R, Ghassemi N, Jafari M, Moridian P, Khadem A, Sadeghi D, Hussain S, Zare A, Sani ZA, Bazeli J, Khozeimeh F, Khosravi A, Nahavandi S, Acharya UR, Shi P (2020) Automated detection and forecasting of COVID-19 using deep learning techniques: a review. arXiv:2007.10785
Shoeibi A, Khodatars M, Jafari M, Moridian P, Rezaei M, Alizadehsani R, Khozeimeh F, Gorriz JM, Heras J, Panahiazar M, Nahavandi S, Acharya UR (2021) Applications of deep learning techniques for automated multiple sclerosis detection using magnetic resonance imaging: a review. Computers in Biology and Medicine. https://www.sciencedirect.com/science/article/pii/S0010482521004911
Simonyan K, Zisserman A (2015) Very deep convolutional networks for large-scale image recognition. In: ICLR
Snavely N, Seitz SM, Szeliski R (2006) Photo tourism: exploring photo collections in 3d. ACM Trans Graph 25(3):835–846
Sun X, Wu J, Zhang X, Zhang Z, Zhang C, Xue T, Tenenbaum J, Freeman WT (2018) Pix3d: dataset and methods for single-image 3d shape modeling. In: CVPR, pp 2974–2983. IEEE computer society
Tatarchenko M, Dosovitskiy A, Brox T (2016) Multi-view 3d models from single images with a convolutional network. In: ECCV (7), lecture notes in computer science, vol 9911, pp 322–337. Springer
Tatarchenko M, Dosovitskiy A, Brox T (2017) Octree generating networks: efficient convolutional architectures for high-resolution 3d outputs. In: ICCV, pp 2107–2115. IEEE computer society
Tulsiani S, Efros AA, Malik J (2018) Multi-view consistency as supervisory signal for learning shape and pose prediction. In: CVPR, pp 2897–2905. IEEE computer cociety
Tulsiani S, Zhou T, Efros AA, Malik J (2017) Multi-view supervision for single-view reconstruction via differentiable ray consistency. In: CVPR, pp 209–217. IEEE computer society
Wang K, Chen K, Jia K (2019) Deep cascade generation on point sets. In: IJCAI, pp 3726–3732. ijcai.org
Wang N, Zhang Y, Li Z, Fu Y, Liu W, Jiang Y (2018) Pixel2mesh: generating 3d mesh models from single RGB images. In: ECCV (11), lecture notes in computer science, vol. 11215, pp 55–71. Springer
Wen C, Zhang Y, Li Z, Fu Y (2019) Pixel2mesh++: multi-view 3d mesh generation via deformation. In: ICCV, pp 1042–1051. IEEE
Witkin AP (1981) Recovering surface shape and orientation from texture. Artif Intell 17(1–3):17–45
Wu J, Wang Y, Xue T, Sun X, Freeman B, Tenenbaum J (2017) Marrnet: 3d shape reconstruction via 2.5d sketches. In: NIPS, pp 540–550
Wu J, Zhang C, Xue T, Freeman B, Tenenbaum J (2016) Learning a probabilistic latent space of object shapes via 3d generative-adversarial modeling. In: NIPS, pp 82–90
Wu J, Zhang C, Zhang X, Zhang Z, Freeman WT, Tenenbaum J (2018) Learning shape priors for single-view 3d completion and reconstruction. In: ECCV (11), lecture notes in computer science, vol 11215, pp 673–691. Springer
Xie H, Yao H, Sun X, Zhou S, Zhang S (2019) Pix2vox: context-aware 3d reconstruction from single and multi-view images. In: ICCV, pp 2690–2698. IEEE
Xu Q, Wang W, Ceylan D, Mech R, Neumann U (2019) DISN: deep implicit surface network for high-quality single-view 3d reconstruction. In: NeurIPS, pp 490–500
Yan X, Yang J, Yumer E, Guo Y, Lee H (2016) Perspective transformer nets: learning single-view 3d object reconstruction without 3d supervision. In: NIPS, pp 1696–1704
Yang B, Rosa S, Markham A, Trigoni N, Wen H (2019) Dense 3d object reconstruction from a single depth view. IEEE Trans Pattern Anal Mach Intell 41(12):2820–2834
Yang B, Wang S, Markham A, Trigoni N (2020) Robust attentional aggregation of deep feature sets for multi-view 3d reconstruction. Int J Comput Vis 128(1):53–73
Yao Y, Schertler N, Rosales E, Rhodin H, Sigal L, Sheffer A (2020) Front2back: single view 3d shape reconstruction via front to back prediction. In: CVPR, pp 528–537. IEEE
Zhu C, Xu K, Chaudhuri S, Yi R, Zhang H (2018) SCORES: shape composition with recursive substructure priors. ACM Trans Graph 37(6):211,1–211,14
Funding
This work is supported by the National Natural Science Foundation of China No.42075139, 42077232, 61272219; the National High Technology Research and Development Program of China No. 2007AA01Z334; the Science and technology program of Jiangsu Province No. BE2020082, BE2010072, BE2011058, BY2012190; the China Postdoctoral Science Foundation No. 2017M621700 and Innovation Fund of State Key Laboratory for Novel Software Technology No. ZZKT2018A09.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of Interests
The authors declare that there is no conflict of interest.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhong, Y., Sun, Z., Luo, S. et al. Video supervised for 3D reconstruction from single image. Multimed Tools Appl 81, 15061–15083 (2022). https://doi.org/10.1007/s11042-022-12459-1
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-022-12459-1