paper-with-me

Papers

ConVRT: Consistent Video Restoration Through Turbulence with Test-time Optimization of Neural Video Representations

2023-12-07 · Haoming Cai, Jingxi Chen, Brandon Y. Feng, Weiyun Jiang, Mingyang Xie, Kevin Zhang, Ashok Veeraraghavan, Christopher Metzler

tmospheric turbulence presents a significant challenge in long-range imaging. Current restoration algorithms often struggle with temporal inconsistency, as well as limited generalization ability across varying turbulence levels and scene content different than the training data. To tackle these issues, we introduce a self-supervised method, Consistent Video Restoration through Turbulence (ConVRT) a test-time optimization method featuring a neural video representation designed to enhance temporal consistency in restoration. A key innovation of ConVRT is the integration of a pretrained vision-language model (CLIP) for semantic-oriented supervision, which steers the restoration towards sharp, photorealistic images in the CLIP latent space. We further develop a principled selection strategy of text prompts, based on their statistical correlation with a perceptual metric. ConVRT's test-time optimization allows it to adapt to a wide range of real-world turbulence conditions, effectively leveraging the insights gained from pre-trained models on simulated data. ConVRT offers a comprehensive and effective solution for mitigating real-world turbulence in dynamic videos.

📄 PDF Abstract BibTeX arXiv:2312.04679

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingVideo Restoration

Methods 이 논문이 사용한 방법론

CLIP Contrastive Language-Image Pre-training (CLIP), consisting of a simplified version of ConVIRT trained from scratch, is an efficient method of image representation learning…

Similar Papers 제목 키워드 기반

PMR: Physical Model-Driven Multi-Stage Restoration of Turbulent Dynamic Videos

2025-08-01 · Tao Wu, Jingyuan Ye, Ying Fu arxiv

Geometric distortions and blurring caused by atmospheric turbulence degrade the quality of long-range dynamic scene videos. Existing methods struggle with restoring edge details and eliminating mixed distortions, especia…

Motion SegmentationVideo Restoration

Turb-Seg-Res: A Segment-then-Restore Pipeline for Dynamic Videos with Atmospheric Turbulence

2024-04-21 · CVPR 2024 1 · Ripon Kumar Saha, Dehao Qin, Nianyi Li, Jinwei Ye 외

Tackling image degradation due to atmospheric turbulence, particularly in dynamic environment, remains a challenge for long-range imaging systems. Existing techniques have been primarily designed for static scenes or sce…

Motion SegmentationOptical Flow EstimationSegmentationVideo Restoration

Subsampled Turbulence Removal Network

2018-07-12 · Wai Ho Chak, Chun Pong Lau, Lok Ming Lui

We present a deep-learning approach to restore a sequence of turbulence-distorted video frames from turbulent deformations and space-time varying blurs. Instead of requiring a massive training sample size in deep network…

Data Augmentation

RMFAT: Recurrent Multi-scale Feature Atmospheric Turbulence Mitigator

2025-08-15 · Zhiming Liu, Nantheera Anantrasirichai arxiv

Atmospheric turbulence severely degrades video quality by introducing distortions such as geometric warping, blur, and temporal flickering, posing significant challenges to both visual clarity and temporal consistency. C…

Video Restoration

Physical prior guided cooperative learning framework for joint turbulence degradation estimation and infrared video restoration

2024-08-08 · Ziran Zhang, YuHang Tang, Zhigang Wang, Yueting Chen 외

Infrared imaging and turbulence strength measurements are in widespread demand in many fields. This paper introduces a Physical Prior Guided Cooperative Learning (P2GCL) framework to jointly enhance atmospheric turbulenc…

Image RestorationVideo Restoration