請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88399
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 吳沛遠 | zh_TW |
dc.contributor.advisor | Pei-Yuan Wu | en |
dc.contributor.author | 葉柏宏 | zh_TW |
dc.contributor.author | Po-Hung Yeh | en |
dc.date.accessioned | 2023-08-15T16:06:59Z | - |
dc.date.available | 2023-11-10 | - |
dc.date.copyright | 2023-08-15 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2023-07-25 | - |
dc.identifier.citation | Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein generative adversarial networks. In International Conference on Machine Learning. PMLR.
Belhumeur, P., Kriegman, D., & Yuille, A. (1997). The bas-relief ambiguity. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Chandraker, M., Kahl, F., & Kriegman, D. (2005). Reflections on the generalized bas-relief ambiguity. In 2005 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Chen, G., Han, K., Shi, B., Matsushita, Y., & Wong, K.-Y. K. (2019). Sdps-net: Self-calibrating deep photometric stereo networks. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Chen, G., Han, K., Shi, B., Matsushita, Y., & Wong, K.-Y. K. (2020). Deep photometric stereo for non-Lambertian surfaces. IEEE Transactions on Pattern Analysis and Machine Intelligence. Chen, G., Waechter, M., Shi, B., Wong, K.-Y. K., & Matsushita, Y. (2020). What is learned in deep uncalibrated photometric stereo? In European Conference on Computer Vision. Riba, D. P. E., & Mishkin, D. (2020). Kornia: An open-source differentiable computer vision library for PyTorch. In Winter Conference on Applications of Computer Vision. Grama, A., Karypis, G., Kumar, V., & Gupta, A. (2003). Introduction to Parallel Computing. Addison-Wesley, second edition. Ikehata, S. (2018). Cnn-ps: CNN-based photometric stereo for general non-convex surfaces. In Proceedings of the European Conference on Computer Vision. Ikehata, S., Wipf, D., Matsushita, Y., & Aizawa, K. (2012). Robust photometric stereo using sparse regression. In 2012 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Kaya, B., Kumar, S., Oliveira, C., Ferrari, V., & Van Gool, L. (2021). Uncalibrated neural inverse rendering for photometric stereo of general surfaces. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Lane, J., & Carpenter, L. (1979). A generalized scan line algorithm for the computer display of parametrically defined surfaces. Computer Graphics and Image Processing. Li, J., & Li, H. (2022). Neural reflectance for shape recovery with shadow handling. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Li, J., & Li, H. (2022). Self-calibrating photometric stereo by neural inverse rendering. In European Conference on Computer Vision. Li, J., Robles-Kelly, A., You, S., & Matsushita, Y. (2019). Learning to minify photometric stereo. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Lin, X., Ding, C., Zeng, J., & Tao, D. (2020). GPS-net: Graph property sensing network for scene graph generation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Logothetis, F., Budvytis, I., Mecca, R., & Cipolla, R. (2021). PX-net: Simple and efficient pixel-wise training of photometric stereo networks. In Proceedings of the IEEE/CVF International Conference on Computer Vision. Loshchilov, I., & Hutter, F. (2019). Decoupled weight decay regularization. In International Conference on Learning Representations. Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2021). NeRF: Representing scenes as neural radiance fields for view synthesis. Communications of the ACM. Santo, H., Samejima, M., Sugano, Y., Shi, B., & Matsushita, Y. (2017). Deep photometric stereo network. In Proceedings of the IEEE International Conference on Computer Vision Workshops. Shi, B., Wu, Z., Mo, Z., Duan, D., Yeung, S.-K., & Tan, P. (2016). A benchmark dataset and evaluation for non-lambertian and uncalibrated photometric stereo. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Taniai, T., & Maehara, T. (2018). Neural inverse rendering for general reflectance photometric stereo. In International Conference on Machine Learning. PMLR. Tiwari, A., & Raman, S. (2022). LERPs: Lighting estimation and relighting for photometric stereo. In ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Wang, X., Jian, Z., & Ren, M. (2020). Non-Lambertian photometric stereo network based on inverse reflectance model with collocated light. IEEE Transactions on Image Processing. Woodham, R. J. (1979). Photometric stereo: A reflectance map technique for determining surface orientation from image intensity. In Image Understanding Systems and Industrial Applications I, volume 155. SPIE. Wu, L., Ganesh, A., Shi, B., Matsushita, Y., Wang, Y., & Ma, Y. (2011). Robust photometric stereo via low-rank matrix completion and recovery. In Asian Conference on Computer Vision. Wu, Z., & Li, L. (1988). A line-integration based method for depth recovery from surface normals. Computer Vision, Graphics, and Image Processing. Yang, W., Chen, G., Chen, C., Chen, Z., & Wong, K.-Y. K. (2022). PS-NERF: Neural inverse rendering for multi-view photometric stereo. In European Conference on Computer Vision. Springer. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/88399 | - |
dc.description.abstract | 儘管在各種應用中具有價值,但由於沒有考慮在不同的物體幾何形狀和變化的照明條件下進行精確的陰影估計,傳統的光度立體方法面臨了限制。為了解決這個問題,我們提出了一種基於並行前綴採樣方法的快速而精確的陰影估計演算法,並且使用一個可微分的溫度函數。我們提出的方法可以輕易地用於改進現有的光度立體方法,以更好地估計陰影的結果。
此外,我們進一步通過我們提出的更高階導數損失配置來提高性能。 為了評估我們方法的有效性,我們進行了全面的實驗並將我們的結果與多種無監督和監督方法進行比較。結果表明,我們的方法在平均角誤差(MAE)方面始終優於其他最先進的無監督方法,同時與監督技術保持競爭力。 | zh_TW |
dc.description.abstract | Although valuable in various applications, traditional photometric stereo approaches have faced limitations due to not considering accurate shadow estimation under different object geometry and varying lighting conditions. We propose a fast and precise shadow estimation algorithm based on a parallel prefix-based sampling method with a differentiable temperature function to address this issue. The proposed method can be easily used to improve existing photometric stereo methods for better estimation of shadow estimation results. In addition, we further improve the performance with our proposed higher-order derivation loss configuration. To assess the effectiveness of our method, we conduct comprehensive experiments and compare our results with diverse unsupervised and supervised approaches. The results demonstrate that our method consistently outperforms other state-of-the-art unsupervised methods regarding mean angular error (MAE) while remaining competitive with supervised techniques. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-08-15T16:06:59Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2023-08-15T16:06:59Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | **Table of Contents**
**Acknowledgements** ........................................... iii **摘要** ............................................ v **Abstract** ............................................ vii **List of Figures** ................................................ xi **List of Tables** ................................................ xiii **Denotation** ................................................... xv **Chapter 1: Introduction** - What is Photometric Stereo .................................... 1 - Overview of the Thesis ......................................... 2 **Chapter 2: Related Works** - Supervised Deep Photometric Stereo ............................. 5 - Neural Inverse Rendering in Photometric Stereo ................ 6 - NeRF Based Methods on Photometric Stereo ...................... 6 **Chapter 3: Problem Formulation** - Photometric Stereo Module ..................................... 9 - Shadow Estimation Module .................................. 10 - Optimization Loss .......................................... 11 - Geometric Constraint and Autograd Losses ................. 11 - Reprojection Loss ........................................ 11 - Closed-form Differentiable Shadow Estimation ................. 12 - Shadow Estimation from Depth Map .......................... 12 - Dynamic Programming Shadow Estimation (DPSE) ............ 13 - Differentiable Dynamic Programming Shadow Estimation (DDPSE) ............................. 14 **Chapter 4: Experiments** - Implementation Details ....................................... 21 - Training Details .............................................. 21 - Evaluation Results with Other SOTA Methods ................... 22 - Evaluation Results with Ground-Truth Depth ................... 24 - Ablation Study ............................................... 24 - Configuration of the Autograd Loss ........................... 26 - Computational Cost and Accuracy on Shadow Estimation ......... 27 **Chapter 5: Conclusion** ........................................ 29 **References** .................................................. 31 | - |
dc.language.iso | en | - |
dc.title | 透過高效且可微的陰影估計提升光度立體 | zh_TW |
dc.title | Improved Photometric Stereo through Efficient and Differentiable Shadow Estimation | en |
dc.type | Thesis | - |
dc.date.schoolyear | 111-2 | - |
dc.description.degree | 碩士 | - |
dc.contributor.coadvisor | 陳駿丞 | zh_TW |
dc.contributor.coadvisor | Jun-Cheng Chen | en |
dc.contributor.oralexamcommittee | 陳祝嵩;莊永裕;劉邦鋒 | zh_TW |
dc.contributor.oralexamcommittee | Chu-Song Chen;Yung-Yu Zhuang;Pang Feng Liu | en |
dc.subject.keyword | 動態規劃,平行前綴掃描,NeRF,光度學立體,深度學習, | zh_TW |
dc.subject.keyword | Dynamic Programming,Parallel Prefix Scan,NeRF,Photometric Stereo,Deep Learning, | en |
dc.relation.page | 34 | - |
dc.identifier.doi | 10.6342/NTU202301876 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2023-07-26 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 資料科學學位學程 | - |
顯示於系所單位: | 資料科學學位學程 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-111-2.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 2.56 MB | Adobe PDF | 檢視/開啟 |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。