Sparse light field imaging often limits the quality of 3D scene reconstruction due to insufficient viewpoint coverage, resulting in incomplete or inaccurate reconstructions. This work introduces a hybrid CNN–LSTM-based framework to address this issue by generating novel camera poses and the corresponding synthesized novel views, effectively densifying the light field representation. The CNN extracts spatial features from the sparse input views, while the LSTM predicts temporal and positional dependencies, enabling smooth interpolation of novel poses and views. The proposed method integrates these synthesized views with the original sparse dataset to produce a comprehensive set of images. Our approach was evaluated on several datasets, including challenging datasets. The inference capability of our method was tested extensively, and it showed good generalization across diverse datasets. The effectiveness of the framework was evaluated not only with local light field fusion (LLFF) but also with NeRF and 3D Gaussian Splatting, which are considered state-of-the-art reconstruction methods. Overall, the enriched dataset generated by our method led to consistent improvements in 3D reconstruction quality, including higher depth estimation accuracy, reduced artifacts, and enhanced structural consistency. Most importantly, LSTM-based approaches have so far attracted limited attention in the context of generating novel views. While LSTMs have been widely applied in sequential data domains such as natural language processing, their use for image generation conditioned on camera poses remains largely unexplored, which underscores the novelty and significance of the proposed work. This approach provides a scalable and generalizable solution to the sparsity problem in light fields, advancing the capabilities of computational imaging, photorealistic rendering, and immersive 3D scene reconstruction. The results firmly establish the proposed method as a robust and versatile tool for improving reconstruction quality in sparse-view settings.
8 June 2025 in ENVIRONMENT. TECHNOLOGIES. RESOURCES. Proceedings of the International Scientific and Practical Conference
Groundwater monitoring is crucial, particularly in drought-prone areas. Manual methods are time-consuming, inaccurate and weather-dependent. GSM solutions are costly and energy-intensive with limited network coverage and other currently existing works and methodologies have certain limitations. Taking these, other factors and limitations into consideration when it comes to monitoring underground water, this research presents an innovative automated system using energy-efficient LoRa technology for real-time monitoring, enhancing efficiency and reliability while reducing costs and energy consumption. The main purpose of this study is to develop and validate an innovative automated groundwater monitoring system that employs energy-efficient LoRa technology for real-time data collection and analysis, thereby overcoming the limitations of manual methods and traditional GSM solutions while ensuring enhanced reliability, scalability and cost-effectiveness. Additionally, the main contribution is the development of an innovative system used for underground water monitoring and comparison of effectiveness of LoRa based network with the GSM based network, comparing the effectiveness of this system with different network topologies when it comes to establishing such a system. Star, line and mesh network topologies were deployed to optimize data transmission and energy efficiency, packet loss and latency of these topologies were evaluated, thus enabling innovative continuous and automated groundwater monitoring. Results show the LoRa-based system significantly reduces energy consumption and operational costs compared to GSM with reliable data transmission even in areas with limited mobile coverage. This research and validation demonstrate the feasibility and advantages of integrating LoRa technology with different topologies into groundwater monitoring systems, providing a scalable solution for sustainable water management, especially in water-scarce regions. Wireshark was used to analyze the results in terms of latency, considering the convenience of the different topologies in different scenarios. The Introduction section highlights the topicality of the topic, study purpose and reviews the current state-of-the-art with limitations of existing approaches addressed by this research. The Materials and Methods section details the design and implementation of the system, with the Results and Discussion section presenting our findings. Finally, the Conclusion section discusses the scientific contributions and value of our research and outlines potential areas for further improvement.