SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2204.02663 · CVPR · 2022

Towards An End-to-End Framework for Flow-Guided Video Inpainting

Zhen Li, Ming-Ming Cheng, Chun-Le Guo, Guo, Cheng-Ze Lu, Jianhua Qin

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 6 functions out of this paper's own repositories and ran 5 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
MCG-NKU/E2FGVI — 5 of 6
FunctionStatusWhere it lives
FusionFeedForward Ran MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("10f2b19d708c1701")
WindowAttention Ran MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("eeb100b4e1aafeeb")
window_partition Ran MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("e68e68741e8501f2")
window_partition_noreshape Ran MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("9805146660e3f049")
window_reverse Ran MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("68e6c97609abe2ea")
TemporalFocalTransformerBlock Not yet run MCG-NKU/E2FGVI/model/modules/tfocal_transformer.py
pointer only (licence: NOASSERTION) · get_code("1e2c1178f8d5b6f2")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Optical flow, which captures motion information across frames, is exploited in recent video inpainting methods through propagating pixels along its trajectories. However, the hand-crafted flow-based processes in these methods are applied separately to form the whole inpainting pipeline. Thus, these methods are less efficient and rely heavily on the intermediate results from earlier stages. In this paper, we propose an End-to-End framework for Flow-Guided Video Inpainting (E 2 FGVI) through elaborately designed three trainable modules, namely, flow completion, feature propagation, and content hallucination modules. The three modules correspond with the three stages of previous flowbased methods but can be jointly optimized, leading to a more efficient and effective inpainting process. Experimental results demonstrate that the proposed method outperforms state-of-the-art methods both qualitatively and quantitatively and shows promising efficiency. The code is available at https://github.com/MCG-NKU/E2FGVI.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2204.02663")
get_code_for_paper("2204.02663")
have("2204.02663")

Connect an agent — have() is free.