Search papers, labs, and topics across Lattice.
This paper introduces AbsoluteDegradation, a physics-inspired pipeline for synthesizing realistic film degradations and a new large-scale benchmark for archival film restoration. By modeling the analog-to-digital process through a structured composition of various artifact families, the pipeline enables the generation of diverse and temporally coherent degradation regimes. Experiments demonstrate that models trained with this approach significantly outperform existing methods on real-world footage, highlighting systematic failure modes in current restoration techniques.
Models trained with AbsoluteDegradation not only generalize better to real archival footage but also expose critical weaknesses in existing restoration methods.
Restoring archival film remains a fundamentally challenging problem due to the absence of paired training data and the lack of standardized evaluation benchmarks. Pristine versions of deteriorated footage are physically unrecoverable, requiring supervised methods to rely on synthetic data that often fail to capture the complex, temporally coherent nature of real film degradation. At the same time, existing real-world datasets are limited in scale, quality, and accessibility, hindering reliable evaluation and fair comparison across methods. We address both limitations with AbsoluteDegradation, a physics-inspired, modular pipeline for synthesizing realistic film degradations, and a new large-scale archival benchmark. The proposed pipeline models the analog-to-digital process as a structured composition of artifact families, incorporating signal-dependent grain, parametric scratches, and temporally coherent camera motion, enabling controlled generation of diverse degradation regimes. In parallel, we introduce a curated dataset of 81,576 high-resolution frames sourced from real archival footage, designed for consistent evaluation under real-world conditions. Together, these contributions provide a unified framework for training and benchmarking restoration models. Extensive experiments across multiple architectures show that models trained with AbsoluteDegradation generalize better to real-world footage, while the proposed benchmark reveals systematic failure modes of current methods. We hope this work establishes a foundation for reproducible and domain-authentic evaluation in archival film restoration.
