Dong Liu*

2 accepted papers

2024

Confidence-Based Iterative Generation for Real-World Image Super-Resolution

Jialun Peng, Xin Luo, Jingjing Fu*, Dong Liu*

ECCV 2024poster

"Real-world image super-resolution deals with complex and unknown degradations, making it challenging to produce plausible results in a single step. In this work, we propose a transformer model with an iterative generation process that iteratively refines the results based on predicted confidences.…

Cited by 0 Source ↗PDF ↗Scholar ↗

2024

Decomposition Betters Tracking Everything Everywhere

Rui Li, Dong Liu*

ECCV 2024poster

"Recent studies on motion estimation have advocated an optimized motion representation that is globally consistent across the entire video, preferably for every pixel. This is challenging as a uniform representation may not account for the complex and diverse motion and appearance of natural videos.…

Cited by 3 Source ↗PDF ↗code ↗Scholar ↗