Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{204429,
        author = {Miss Simantinee Shinde and Dr J A Shaikh},
        title = {Learning-Based Automatic 2D-to-3D Image Conversion Using Local Point Transformation and Depth Estimation},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {1},
        pages = {2925-2930},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=204429},
        abstract = {The work presents a simple automatic 2D to 3D image conversion using Local Point Transformation Learning. The method uses the NY Depth Dataset for training and testing. Different local image features such as grayscale intensity, edge information and mean filtered values are extracted from the image. These features are used to train a regression model for depth prediction. The predicted depth map is improved using bilateral filtering to reduce noise and preserve edges. Using depth information, a right stereo image is generated from the original image. Finally, 3D anaglyph image is created by combining the left and right views. The performance of the method is evaluated using RMSE, MAE, PSNR and SSIM parameters.  The results show that the proposed method can generate good quality depth maps and realistic 3D images with low computational.},
        keywords = {2D to 3D conversion, depth estimation, Local Point Transformation, NYU depth dataset, stereo image generation.},
        month = {June},
        }