A new Interval Denoiser target gives 4.55 FID at 1 step and 3.98 FID at 2 steps for pixel-space ImageNet 256 generation, without perceptual losses.
InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 10684–10695
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Rethinking Pixel Mean Flows via Interval Denoiser
A new Interval Denoiser target gives 4.55 FID at 1 step and 3.98 FID at 2 steps for pixel-space ImageNet 256 generation, without perceptual losses.