NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration: Methods and Results

2026-04-08

AI Summary

This work addresses the severe spatiotemporal artifacts and content distortion caused by corrupted video bitstreams by establishing, for the first time, a unified evaluation benchmark tailored to this scenario. The benchmark comprises a practical dataset, a standardized evaluation protocol, and a public challenge that aggregates diverse state-of-the-art video restoration algorithms. Emphasis is placed on modeling spatiotemporal consistency, understanding bitstream-distortion-aware mechanisms, and designing end-to-end deep learning architectures. Through comprehensive analysis of the submitted methods, the study delineates the current performance limits and identifies key challenges in robust video restoration, offering valuable insights and clear directions for future research in this domain.

Abstract

This paper reports on the NTIRE 2026 Challenge on Bitstream-Corrupted Video Restoration (BSCVR). The challenge aims to advance research on recovering visually coherent videos from corrupted bitstreams, whose decoding often produces severe spatial-temporal artifacts and content distortion. Built upon recent progress in bitstream-corrupted video recovery, the challenge provides a common benchmark for evaluating restoration methods under realistic corruption settings. We describe the dataset, evaluation protocol, and participating methods, and summarize the final results and main technical trends. The challenge highlights the difficulty of this emerging task and provides useful insights for future research on robust video restoration under practical bitstream corruption.

Problem

• bitstream corruption
• video restoration
• spatial-temporal artifacts
• content distortion
• visual coherence

Innovation

• Bitstream-Corrupted Video Restoration
• Video Recovery
• Temporal-Spatial Artifacts
• Robust Video Restoration
• NTIRE Challenge