Mikołaj Jastrzębski

Machine learning engineer and researcher. First author of two papers on archival film restoration, accepted at NeurIPS 2026 and ACCV 2026, with production experience in agentic and generative AI.

Publications

• DART: A Degradation-Aware Recurrent Transformer for Archival Film Restoration
  Mikołaj Jastrzębski, Wojciech Kozłowski, Kamil Adamczewski
  Asian Conference on Computer Vision (ACCV) 2026. Paper (arXiv:2607.21219) · PDF · Code
  A degradation-aware recurrent transformer that predicts a soft defect mask and propagates it through time - reasoning explicitly about where footage is damaged and how severely, instead of reconstructing frames blindly.
• AbsoluteDegradation: A Physics-Inspired Synthetic Film-Degradation Pipeline and Archival Film Restoration Benchmark
  Mikołaj Jastrzębski, Dawid Glinkowski, Dawid Zieliński, Daniel Borkowski, Wojciech Kozłowski, Kamil Adamczewski
  Conference on Neural Information Processing Systems (NeurIPS) 2026, Evaluations and Datasets Track. Paper (arXiv:2607.02131) · PDF · Code
  A physics-inspired pipeline that models the full analog-to-digital chain - signal-dependent grain, mean-reverting gate-weave and parametric scratches - paired with a new large-scale real-world archival benchmark.

Links

CV (PDF) · linkedin.com · github.com · scholar.google.com · orcid.org · huggingface.co · openreview.net · [email protected]