DOAJ Open Access 2026

Text-guided diffusion-based restoration of extremely compressed backgrounds for VCM

Le Thi Hue Dao Naeun Yang Jooyoung Lee Seyoon Jeong Chul Lee

Abstrak

Restoring high-quality images from severely degraded inputs is essential for video coding for machines (VCM), where background regions are compressed at extremely low bitrates. In this letter, we propose a novel text-guided diffusion-based restoration (TGDR) algorithm, which integrates semantic information from text captions to guide the restoration process. Specifically, we develop a refinement block that incorporates a transformer-based time-aware feature extractor to fuse visual features, time-step embeddings, and textual semantics adaptively to guide a pretrained diffusion model during the reverse denoising process. By incorporating both visual and textual information, TGDR effectively reconstructs complex structures and improves semantic consistency in highly compressed regions. Experimental results show that TGDR achieves superior performance compared to state-of-the-art algorithms.

Topik & Kata Kunci

Penulis (5)

L

Le Thi Hue Dao

N

Naeun Yang

J

Jooyoung Lee

S

Seyoon Jeong

C

Chul Lee

Format Sitasi

Dao, L.T.H., Yang, N., Lee, J., Jeong, S., Lee, C. (2026). Text-guided diffusion-based restoration of extremely compressed backgrounds for VCM. https://doi.org/10.1016/j.icte.2026.01.011

Akses Cepat

PDF tidak tersedia langsung

Cek di sumber asli →
Lihat di Sumber doi.org/10.1016/j.icte.2026.01.011
Informasi Jurnal
Tahun Terbit
2026
Sumber Database
DOAJ
DOI
10.1016/j.icte.2026.01.011
Akses
Open Access ✓