@article{ART003204578},
author={Jong-Su Ha and Young-Soo Kwon and Jin-Ah Kim and Yoo-Joo Choi},
title={Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={5},
pages={9-20}
TY - JOUR
AU - Jong-Su Ha
AU - Young-Soo Kwon
AU - Jin-Ah Kim
AU - Yoo-Joo Choi
TI - Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 5
PB - The Korean Society Of Computer And Information
SP - 9
EP - 20
SN - 1598-849X
AB - Using deep neural networks such as NoPe-NeRF, it has been observed that when generating 2D synthesized images from arbitrary viewpoints—after learning 3D spatial information from 2D input images without prior camera information—the image quality in distant regions tends to degrade significantly. This paper proposes a method to address the issue of image quality degradation in distant regions of synthesized images. The degradation is presumed to result from the use of inaccurately matched point pairs with low correspondence accuracy when computing the point cloud loss function in NoPe-NeRF. To mitigate this problem, we incorporate a Probabilistic Dense Correspondence Network (PDCNet) to improve point matching accuracy between adjacent camera images. These refined correspondences are then used to compute a more reliable point cloud loss. The effectiveness of the proposed method is validated through quantitative evaluation using PSNR, SSIM, and LPIPS, as well as qualitative visual comparisons. Furthermore, to assess improvements in camera pose estimation, ATE and RPE metrics are compared before and after applying our method. The results demonstrate that the proposed approach not only enhances the visual quality of synthesized images from arbitrary viewpoints but also improves the accuracy of camera pose estimation.
KW - Synthesized Image Generation;3D Spatial Estimation;NeRF;and Probabilistic Dense Correspondence Networks
DO -
UR -
ER -
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim and Yoo-Joo Choi. (2025). Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching. Journal of The Korea Society of Computer and Information, 30(5), 9-20.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim and Yoo-Joo Choi. 2025, "Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching", Journal of The Korea Society of Computer and Information, vol.30, no.5 pp.9-20.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim, Yoo-Joo Choi "Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching" Journal of The Korea Society of Computer and Information 30.5 pp.9-20 (2025) : 9.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim, Yoo-Joo Choi. Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching. 2025; 30(5), 9-20.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim and Yoo-Joo Choi. "Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching" Journal of The Korea Society of Computer and Information 30, no.5 (2025) : 9-20.
Jong-Su Ha; Young-Soo Kwon; Jin-Ah Kim; Yoo-Joo Choi. Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching. Journal of The Korea Society of Computer and Information, 30(5), 9-20.
Jong-Su Ha; Young-Soo Kwon; Jin-Ah Kim; Yoo-Joo Choi. Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching. Journal of The Korea Society of Computer and Information. 2025; 30(5) 9-20.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim, Yoo-Joo Choi. Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching. 2025; 30(5), 9-20.
Jong-Su Ha, Young-Soo Kwon, Jin-Ah Kim and Yoo-Joo Choi. "Image quality enhancement for arbitrary viewpoint synthesis based on accurate inter-camera point matching" Journal of The Korea Society of Computer and Information 30, no.5 (2025) : 9-20.
