The authors separate distributional training into two choices: how feature distributions are represented and which discrepancy is minimized between them.
Gaussian mixtures improve distributional training for one-step image generators
MGFlow matches real and generated feature distributions at adjustable granularity, improving ImageNet results and enabling one-step text-to-image generation.
Top University
Chi Zhang · Haoyang Shi · Yueyi Liu · Ruichuan An · Junkang Zhou · Chang Li · +6 more
Tsinghua University · Fudan University · Xi’an Jiaotong University · Peking University · Zhejiang University
Research Digest··2 min read
Zhang, Shi, Liu and colleagues present a common mathematical account of distributional training, where generators learn by matching collections of real and generated features from frozen image encoders.
Why this paper
From Tsinghua University and 6 others · Released code
In one line
MGFlow uses Gaussian mixture modeling and mass-constrained assignment to achieve state-of-the-art one-step visual generation.
What it released
Code
What we could check
- ✓Code link in the paper (github.com)
- ·No weights link found
- ·No dataset link found
- ·No compute details found
- ·No stated limitations found
- ✓Reports numbers on named benchmarks
Observed from the paper text and links we have. Absence here means we did not find it, not that it does not exist.
§