Aligning the L2-norm statistics of noise predictions during diffusion sampling improves domain adaptation for dense prediction, with a source-free version guided by high-confidence regions.
Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Recently, Google proposes DDVM which for the first time demonstrates that a general diffusion model for image-to-image translation task works impressively well on optical flow estimation task without any specific designs like RAFT. However, DDVM is still a closed-source model with the expensive and private Palette-style pretraining. In this technical report, we present the first open-source DDVM by reproducing it. We study several design choices and find those important ones. By training on 40k public data with 4 GPUs, our reproduction achieves comparable performance to the closed-source DDVM. The code and model have been released in https://github.com/DQiaole/FlowDiffusion_pytorch.
citation-role summary
baseline 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
baseline 1polarities
baseline 1representative citing papers
citing papers explorer
-
FreeDNA: Endowing Domain Adaptation of Diffusion-Based Dense Prediction with Training-Free Domain Noise Alignment
Aligning the L2-norm statistics of noise predictions during diffusion sampling improves domain adaptation for dense prediction, with a source-free version guided by high-confidence regions.