REVIEW 7 cited by
gDDIM: Generalized denoising diffusion implicit models
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
Our goal is to extend the denoising diffusion implicit model (DDIM) to general diffusion models~(DMs) besides isotropic diffusions. Instead of constructing a non-Markov noising process as in the original DDIM, we examine the mechanism of DDIM from a numerical perspective. We discover that the DDIM can be obtained by using some specific approximations of the score when solving the corresponding stochastic differential equation. We present an interpretation of the accelerating effects of DDIM that also explains the advantages of a deterministic sampling scheme over the stochastic one for fast sampling. Building on this insight, we extend DDIM to general DMs, coined generalized DDIM (gDDIM), with a small but delicate modification in parameterizing the score network. We validate gDDIM in two non-isotropic DMs: Blurring diffusion model (BDM) and Critically-damped Langevin diffusion model (CLD). We observe more than 20 times acceleration in BDM. In the CLD, a diffusion model by augmenting the diffusion process with velocity, our algorithm achieves an FID score of 2.26, on CIFAR10, with only 50 number of score function evaluations~(NFEs) and an FID score of 2.86 with only 27 NFEs. Code is available at https://github.com/qsh-zh/gDDIM
Forward citations
Cited by 7 Pith papers
-
RDPO: Real Data Preference Optimization for Physics Consistency Video Generation
RDPO builds preference pairs by reverse-sampling real video latents with a pre-trained generator, then fine-tunes with Flow-DPO, improving physics consistency metrics on two video models.
-
Amortized Moment Matching for Visual Generation
Amortized Fréchet Distance uses neural nets to match conditional means and covariances, yielding stronger one-step visual generators than explicit FD-loss or multi-step teachers.
-
Function-Space Diffusion for Motion Planning
FSD-MP performs diffusion over continuous trajectory functions with Matérn noise and a DST-FNO reverse model, enabling zero-shot multi-resolution robot motion planning.
-
OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer Models
A training-free cache-reuse scheme that spreads computation across the full diffusion trajectory and subtracts estimated noise, accelerating DiT sampling with claimed competitive quality.
-
Suppressing Gradient Conflict for Generalizable Deepfake Detection
Training deepfake detectors on both original and online-synthesized fakes degrades performance due to gradient conflict, and CS-DFD mitigates this with an update-vector search and a conflict-reduction loss.
-
Non-asymptotic convergence bound of conditional diffusion models
CARD's generated conditional distribution is shown to converge in Wasserstein distance to the true conditional distribution, with a separate score-estimation error bound controlled by network resolution and distributi...
-
DualFast: Dual-Speedup Framework for Fast Sampling of Diffusion Models
A training-free correction that blends each step's noise estimate with the initial noise estimate improves few-step diffusion sampling across DDIM, DPM-Solver, and DPM-Solver++.
Discussion (0). Sign in to comment.