REVIEW 5 cited by
FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model
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
Signed reviews
read the original abstract
Recently, conditional diffusion models have gained popularity in numerous applications due to their exceptional generation ability. However, many existing methods are training-required. They need to train a time-dependent classifier or a condition-dependent score estimator, which increases the cost of constructing conditional diffusion models and is inconvenient to transfer across different conditions. Some current works aim to overcome this limitation by proposing training-free solutions, but most can only be applied to a specific category of tasks and not to more general conditions. In this work, we propose a training-Free conditional Diffusion Model (FreeDoM) used for various conditions. Specifically, we leverage off-the-shelf pre-trained networks, such as a face detection model, to construct time-independent energy functions, which guide the generation process without requiring training. Furthermore, because the construction of the energy function is very flexible and adaptable to various conditions, our proposed FreeDoM has a broader range of applications than existing training-free methods. FreeDoM is advantageous in its simplicity, effectiveness, and low cost. Experiments demonstrate that FreeDoM is effective for various conditions and suitable for diffusion models of diverse data domains, including image and latent code domains.
Forward citations
Cited by 5 Pith papers
-
Rethinking Diffusion Posterior Sampling: From Conditional Score Estimator to Maximizing a Posterior
The paper provides evidence that Diffusion Posterior Sampling implicitly maximizes a posterior rather than sampling the posterior, and uses this to build faster, better-performing restoration algorithms.
-
Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model
A conditional latent diffusion model with a wavelet projection module and model-driven sampling performs fast seismic acoustic impedance inversion, with higher well-log correlation than supervised, unsupervised, and t...
-
Incorporating Inductive Biases to Energy-based Generative Models
Augmenting a neural energy-based model with a linear statistic term that encodes known data properties improves generation quality on molecules, digits, and point clouds.
-
Random Sampling for Diffusion-based Adversarial Purification
A maximally random variant of DDIM sampling, combined with guidance applied to the predicted clean image, yields a diffusion purification defense (DiffAP) that outperforms prior methods on CIFAR-10.
-
Test-time Conditional Text-to-Image Synthesis Using Diffusion Models
TINTIN conditions Stable Diffusion outputs at test time on color palettes and edge maps by backpropagating losses between decoded images and the condition through the denoising steps.
Discussion (0). Continue with ORCID to comment.