Image formation using adaptive supersampling with overlap tiles

Authors

DOI:

https://doi.org/10.31649/1681-7893-2026-51-1-90-96

Keywords:

image formation, rendering, realism, photorealism, supersampling, antialiasing, tile decomposition

Abstract

The article proposes a new method of adaptive tile overlapping supersampling (AOTSS). The method is based on dividing the image into square tiles with an additional overlap zone, which eliminates artifacts at the boundaries of adjacent computational blocks. A cubic mixing weight function is used for a smooth transition between tiles. Adaptive distribution of computational resources is implemented through a complexity function that takes into account the intensity gradient, scene depth variation, and edge density. The number of subpixel samples automatically increases in complex areas and decreases in homogeneous areas, which reduces the overall computational load. The mathematical model confirms that the error decreases inversely proportional to the square root of the number of samples, and the tile artifact is eliminated with increasing overlap width. Comparative analysis with MSAA, SSAA, and TAA methods demonstrates the advantages of the proposed approach in terms of quality and performance. The method is promising for integration into GPU-oriented real-time rendering pipelines.

Author Biographies

Yo.Yo. Bilynsky, Vinnytsia National Technical University

Доктор технічних наук, професор кафедри загальної фізики

O.Ya. Stakhov, Vinnytsia National Technical University

Доктор філософії, ст. викладач кафедри програмного забезпечення,

O.V. Kaduk, Vinnytsia National Technical University

Ph.D., доцент кафедри комп’ютерної інженерії

B.V. Babij, Vinnytsia National Technical University

Студент кафедри програмного забезпечення

References

Marrs, J. Spjut, H. Gruen, R. Sathe, and M. McGuire, “Improving Temporal Antialiasing with Adaptive Ray Tracing,” in Ray Tracing GemsI, Berkeley, CA, USA: Apress, 2019, pp. 353–370.

L. Yang, S. Liu, and M. Salvi, “A Survey of Temporal Antialiasing Techniques,” Computer Graphics Forum, vol. 39, no. 2, pp. 607–621, 2020.

Wronski. “Temporal supersampling and antialiasing.” BartWronski.com. https://bartwronski.com/2014/03/15/temporal-supersampling-and-antialiasing/ (accessed May 12, 2026)

Schied, C. Peters, and C. Dachsbacher, “Gradient Estimation for Real-Time Adaptive Supersampling,” Proceedings of the ACM on Computer Graphics and Interactive Techniques, Vol. 1, Issue 2, Art. no. 24, 2018.

B. Jin, I. Ihm, B. Chang, C. Park, W. Lee, and S. Jung, “ Selective and adaptive supersampling for real-time ray tracing,” in HPG '09: Proceedings of the Conference on High Performance Graphics 2009, 2009, pp. 117-125.

L. Xiao, S. Nouri, M. Chapman, A. Fix, D. Lanman, and A. Kaplanyan, “Neural Supersampling for Real-Time Rendering,” ACM Transactions on Graphics (TOG), vol. 39, no. 4, pp. 142:1–142:12, 2020.

Bisikalo, O.; Kharchenko, V.; Kovtun, V.; Krak, I.; Pavlov, S. Parameterization of the Stochastic Model for Evaluating Variable Small Data in the Shannon Entropy Basis. Entropy 2023, 25, 184.

Intellectual technologies in medical diagnostics, treatment and rehabilitation: monograph / [S.V. Pavlov, O.G. Avrunin, S.M. Zlepko, E.V. Bodianskyi and others]; edited by S. Pavlov, O. Avrunin. – Vinnytsia: PP “TD “Edelweiss and K”, 2019. – 260 p.

J. T. Barron, B. Mildenhall, M. Tancik, P. Hedman, R. Martin-Brualla, and P. P. Srinivasan, “Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance Fields,” in Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV), 2021, pp. 5855–5864.

Downloads

Abstract views: 8

Published

2026-06-18

How to Cite

[1]
Y. Bilynsky, O. Stakhov, O. Kaduk, and B. Babij, “Image formation using adaptive supersampling with overlap tiles”, Опт-ел. інф-енерг. техн., vol. 51, no. 1, pp. 90–96, Jun. 2026.

Issue

Section

Systems Of Technical Vision And Artificial Intelligence, Image Processing And Pattern Recognition

Metrics

Downloads

Download data is not yet available.