Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
140 tokens/sec
GPT-4o
8 tokens/sec
Gemini 2.5 Pro Pro
47 tokens/sec
o3 Pro
5 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

3D View Optimization for Improving Image Aesthetics (2405.16443v1)

Published 26 May 2024 in cs.CV and cs.GR

Abstract: Achieving aesthetically pleasing photography necessitates attention to multiple factors, including composition and capture conditions, which pose challenges to novices. Prior research has explored the enhancement of photo aesthetics post-capture through 2D manipulation techniques; however, these approaches offer limited search space for aesthetics. We introduce a pioneering method that employs 3D operations to simulate the conditions at the moment of capture retrospectively. Our approach extrapolates the input image and then reconstructs the 3D scene from the extrapolated image, followed by an optimization to identify camera parameters and image aspect ratios that yield the best 3D view with enhanced aesthetics. Comparative qualitative and quantitative assessments reveal that our method surpasses traditional 2D editing techniques with superior aesthetics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (25)
  1. Optuna: A next-generation hyperparameter optimization framework. In Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, KDD 2019, Anchorage, AK, USA, August 4-8, 2019, pages 2623–2631. ACM, 2019.
  2. Autophoto: Aesthetic photo capture using reinforcement learning. In 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pages 944–951, 2021.
  3. Seam carving for content-aware image resizing. ACM Trans. Graph., 26(3):10, 2007.
  4. Computational zoom: a framework for post-capture image composition. ACM Trans. Graph., 36(4):46:1–46:14, 2017.
  5. Quantitative analysis of automatic image cropping algorithms: A dataset and comparative study. In WACV 2017, pages 226–234. IEEE Computer Society, 2017a.
  6. Learning to compose with professional photographs on the web. In Proceedings of the 25th ACM International Conference on Multimedia, page 37–45, New York, NY, USA, 2017b. Association for Computing Machinery.
  7. Automatic image cropping using visual composition, boundary simplicity and content preservation models. In Proceedings of the 22nd ACM International Conference on Multimedia, page 1105–1108, New York, NY, USA, 2014. Association for Computing Machinery.
  8. Completely derandomized self-adaptation in evolution strategies. Evolutionary computation, 9(2):159–195, 2001.
  9. Rethinking image aesthetics assessment: Models, datasets and benchmarks. In Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence, IJCAI 2022, Vienna, Austria, 23-29 July 2022, pages 942–948, 2022.
  10. Composing photos like a photographer. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 7057–7066, 2021.
  11. Accelerating 3D deep learning with PyTorch3D. In SIGGRAPH Asia 2020 Courses. Association for Computing Machinery, 2020.
  12. Adam: A method for stochastic optimization. In 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings, 2015.
  13. A2-rl: Aesthetics aware reinforcement learning for image cropping. In Proceedings of the IEEE conference on computer vision and pattern recognition, pages 8193–8201, 2018.
  14. Composing good shots by exploiting mutual relations. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 4213–4222, 2020.
  15. Realtime aesthetic image retargeting. In 6th International Symposium on Computational Aesthetics in Graphics, Visualization, and Imaging (CAe 2010), pages 1–8. Eurographics Association, 2010.
  16. ZoomShop: Depth-aware editing of photographic composition. In Computer Graphics Forum, pages 57–70. Wiley Online Library, 2022.
  17. Beyond image borders: Learning feature extrapolation for unbounded image composition. In Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), pages 13023–13032, 2023.
  18. Towards robust monocular depth estimation: Mixing datasets for zero-shot cross-dataset transfer. IEEE Trans. Pattern Anal. Mach. Intell., 44(3):1623–1637, 2022.
  19. A comparative study of image retargeting. ACM Trans. Graph., 29(6), 2010.
  20. 3D photography using context-aware layered depth inpainting. In CVPR 2020, pages 8025–8035. Computer Vision Foundation / IEEE, 2020.
  21. Good view hunting: Learning photo composition from dense view pairs. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5437–5446, 2018.
  22. Gait: Generating aesthetic indoor tours with deep reinforcement learning. In Proceedings of the IEEE/CVF International Conference on Computer Vision, pages 7409–7419, 2023.
  23. Reliable and efficient image cropping: A grid anchor based approach. In 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pages 5942–5950, Los Alamitos, CA, USA, 2019. IEEE Computer Society.
  24. Image composition assessment with saliency-augmented multi-pattern pooling. In BMVC 2021, page 144. BMVA Press, 2021.
  25. Aesthetic-guided outward image cropping. ACM Transactions on Graphics (TOG), 40(6):1–13, 2021.

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets