Kuldeep Singh

As oil marketing companies push cumulative fuel price hikes to ₹7.5 per litre, economists warn of immediate pressure on India's Consumer Price Index (CPI), predicting direct and indirect freight pass-throughs could add up to 60–70 basis points to near-term inflation.

The Ministry of Statistics and Programme Implementation (MoSPI) will roll out a revised Index of Industrial Production (IIP) with a 2022-23 base year, expanding industrial tracking to include rare earth minerals, green energy generation, and waste management sectors.

India’s GDP growth is likely to moderate to 7.2% in the January-March 2026 quarter amid the initial impact of the West Asia crisis, while economists expect full-year FY26 expansion to remain resilient at around 7.6%.

In a judgment with profound implications for the gaming industry, the Supreme Court on Wednesday upheld the constitutional validity of the Centre's

Author(s) Mr. Kuldeep Singh Country India Abstract

India's gross GST collections reached ₹1.94 lakh crore in May 2026, marking a 3.2% year-on-year growth driven by a 19.1% surge in import revenues despite West Asia geopolitical tensions.

Manufacturing, capital goods key drivers under new 2022-23 base year

With this and marginal revisions of growth figures for first three quarters, the gross domestic product (GDP) clocked a creditable 7.7% growth in FY26, the highest in the new series using 2022-23 as the base year.

The "Dalal" Tax: Direct vs Regular Funds "दलाल" टैक्स: डायरेक्ट बनाम रेगुलर फंड If you have finally decided to start your investment journey, congratulations!

Handling unknown degradations remains a fundamental challenge in real-world Single Image Super-Resolution (SISR). Most existing methods rely on supervised training with synthetic Low-Resolution (LR) and High-Resolution (HR) pairs, leading to poor generalization under real-world conditions. To address this, we propose the Generalized Real-world Super-Resolution Generative Adversarial Network (GRSGAN), a novel two-stage framework that robustly recovers high-fidelity images from real degraded inputs without requiring paired data. In the first stage, a Zero-Shot Adaptive Degradation Correction Network (ADCN) estimates and reverses complex, unknown degradations such as noise, blur, and compression artifacts through an internal learning process. In the second stage, an Efficient Super-Resolution Generative Network (ESRG-Net) leverages a lightweight GAN architecture with Depthwise Separable Residual Attention Blocks (DSRAB) to reconstruct perceptually rich and structurally accurate HR images. Training of the ESRG-Net is guided by an edge-aware hybrid loss to balance fidelity and visual realism. While the reconstruction stage is designed for efficiency, the integrated zero-shot optimization ensures high adaptability to diverse real-world artifacts. Evaluation on multiple real-world benchmarks demonstrates that GRSGAN significantly outperforms state-of-the-art methods in both distortion-oriented (PSNR/SSIM) and perception-oriented (LPIPS/NIQE/DISTS) metrics. GRSGAN achieved +1.2dB PSNR gain and 18% lower LPIPS compared to the baseline Real-ESRGAN model on the RealSR dataset. The proposed framework demonstrates strong generalization to unseen degradations and establishes a robust baseline for high-fidelity restoration. Finally, this work also provides a clear foundation for future research toward more efficient, broadly adaptable real-world super-resolution systems.