The authors built a shared clean-target predictor that receives noisy targets and conditioning observations.
One Flow Model Can Reconstruct Scenes or Generate Missing Detail
By changing the number of denoising steps at inference, the same predictor shifts between conservative reconstruction and generative completion.
Top University
Haoru Wang · Qianfan Shen · Kai Ye · Wenzheng Chen · Baoquan Chen
Peking University
Research Digest··3 min read
Wang and colleagues formulate feed-forward reconstruction and conditional generation as two inference modes of one flow-based model.
Why this paper
From Peking University
In one line
A shared clean-target predictor performs direct reconstruction at one step and conditional generation through multi-step flow.
What we could check
- ·No code link found
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ·No benchmark numbers found
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
Concepts
§