REVIEW 2 cited by
Open-DDVM: A Reproduction and Extension of Diffusion Model for Optical Flow Estimation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original 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.
Forward citations
Cited by 2 Pith papers
-
FlowPainter: Inpainting Optical Flow via Confidence-Guided Completion
Confidence-guided soft inpainting lets a lightweight flow prior stabilize and accelerate diffusion-based optical flow, yielding stronger results on Sintel, KITTI, and Spring with fewer training iterations.
-
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.
Discussion (0). Continue with ORCID to comment.