Bitstream-corrupted video recovery: a novel benchmark dataset and method
The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communica...
| Main Authors: | , , , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://hdl.handle.net/10356/174533 https://proceedings.neurips.cc/paper_files/paper/2023 |
| _version_ | 1824456412605972480 |
|---|---|
| author | Liu, Tianyi Wu, Kejun Wang, Yi Liu, Wenyang Yap, Kim-Hui Chau, Lap-Pui |
| author2 | School of Electrical and Electronic Engineering |
| author_facet | School of Electrical and Electronic Engineering Liu, Tianyi Wu, Kejun Wang, Yi Liu, Wenyang Yap, Kim-Hui Chau, Lap-Pui |
| author_sort | Liu, Tianyi |
| collection | NTU |
| description | The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communication (e.g., telepresence, live streaming, and internet video) and multimedia forensics. To address this, we introduce the bitstream-corrupted video (BSCV) benchmark, the first benchmark dataset with more than 28,000 video clips, which can be used for bitstream-corrupted video recovery in the real world.
The BSCV is a collection of
1) a proposed three-parameter corruption model for video bitstream,
2) a large-scale dataset containing rich error patterns, multiple corruption levels, and flexible dataset branches, and
3) a new video recovery framework that serves as a benchmark.
We evaluate state-of-the-art video inpainting methods on the BSCV dataset, demonstrating existing approaches' limitations and our framework's advantages in solving the bitstream-corrupted video recovery problem.
The benchmark and dataset are released at https://github.com/LIUTIGHE/BSCV-Dataset. |
| first_indexed | 2025-02-19T03:53:42Z |
| format | Conference Paper |
| id | ntu-10356/174533 |
| institution | Nanyang Technological University |
| language | English |
| last_indexed | 2025-02-19T03:53:42Z |
| publishDate | 2024 |
| record_format | dspace |
| spelling | ntu-10356/1745332024-04-05T15:40:30Z Bitstream-corrupted video recovery: a novel benchmark dataset and method Liu, Tianyi Wu, Kejun Wang, Yi Liu, Wenyang Yap, Kim-Hui Chau, Lap-Pui School of Electrical and Electronic Engineering 37th Conference on Neural Information Processing Systems (NeurIPS 2023) Computer and Information Science Video Restoration Bitstream Corruption The past decade has witnessed great strides in video recovery by specialist technologies, like video inpainting, completion, and error concealment. However, they typically simulate the missing content by manual-designed error masks, thus failing to fill in the realistic video loss in video communication (e.g., telepresence, live streaming, and internet video) and multimedia forensics. To address this, we introduce the bitstream-corrupted video (BSCV) benchmark, the first benchmark dataset with more than 28,000 video clips, which can be used for bitstream-corrupted video recovery in the real world. The BSCV is a collection of 1) a proposed three-parameter corruption model for video bitstream, 2) a large-scale dataset containing rich error patterns, multiple corruption levels, and flexible dataset branches, and 3) a new video recovery framework that serves as a benchmark. We evaluate state-of-the-art video inpainting methods on the BSCV dataset, demonstrating existing approaches' limitations and our framework's advantages in solving the bitstream-corrupted video recovery problem. The benchmark and dataset are released at https://github.com/LIUTIGHE/BSCV-Dataset. National Research Foundation (NRF) Published version This research is supported by the National Research Foundation, Singapore, and Cyber Security Agency of Singapore under its National Cybersecurity Research & Development Programme (Cyber-Hardware Forensic & Assurance Evaluation R&D Programme (NRF2018NCRNCR009-0001). 2024-04-02T06:34:01Z 2024-04-02T06:34:01Z 2023 Conference Paper Liu, T., Wu, K., Wang, Y., Liu, W., Yap, K. & Chau, L. (2023). Bitstream-corrupted video recovery: a novel benchmark dataset and method. 37th Conference on Neural Information Processing Systems (NeurIPS 2023). https://hdl.handle.net/10356/174533 https://proceedings.neurips.cc/paper_files/paper/2023 en NRF2018NCRNCR009-0001 © 2023 The Author(s). All rights reserved. This article may be downloaded for personal use only. Any other use requires prior permission of the copyright holder. The Version of Record is available online at https://proceedings.neurips.cc/paper_files/paper/2023. application/pdf |
| spellingShingle | Computer and Information Science Video Restoration Bitstream Corruption Liu, Tianyi Wu, Kejun Wang, Yi Liu, Wenyang Yap, Kim-Hui Chau, Lap-Pui Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title | Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title_full | Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title_fullStr | Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title_full_unstemmed | Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title_short | Bitstream-corrupted video recovery: a novel benchmark dataset and method |
| title_sort | bitstream corrupted video recovery a novel benchmark dataset and method |
| topic | Computer and Information Science Video Restoration Bitstream Corruption |
| url | https://hdl.handle.net/10356/174533 https://proceedings.neurips.cc/paper_files/paper/2023 |
| work_keys_str_mv | AT liutianyi bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod AT wukejun bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod AT wangyi bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod AT liuwenyang bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod AT yapkimhui bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod AT chaulappui bitstreamcorruptedvideorecoveryanovelbenchmarkdatasetandmethod |