REVIEW 8 cited by
Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise
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
Standard diffusion models involve an image transform -- adding Gaussian noise -- and an image restoration operator that inverts this degradation. We observe that the generative behavior of diffusion models is not strongly dependent on the choice of image degradation, and in fact an entire family of generative models can be constructed by varying this choice. Even when using completely deterministic degradations (e.g., blur, masking, and more), the training and test-time update rules that underlie diffusion models can be easily generalized to create generative models. The success of these fully deterministic models calls into question the community's understanding of diffusion models, which relies on noise in either gradient Langevin dynamics or variational inference, and paves the way for generalized diffusion models that invert arbitrary processes. Our code is available at https://github.com/arpitbansal297/Cold-Diffusion-Models
Forward citations
Cited by 8 Pith papers
-
CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters
Presents CaloTrilogy, a unified one-step generative model for high-granularity calorimeter showers that combines velocity field integration, learned priors, and physics losses to match SOTA quality.
-
Progressive Checkerboards for Autoregressive Multiscale Image Generation
A balanced multiscale checkerboard sampling order for autoregressive image generation allows large scale-up factors without quality loss, because only the total number of serial steps matters.
-
Higher fidelity perceptual image and video compression with a latent conditioned residual denoising diffusion model
ResCDC combines a fidelity-optimized decoder with a latent-conditioned residual denoising diffusion model to improve PSNR by up to 2 dB over CDC while retaining similar LPIPS and FID.
-
From Missing Pieces to Masterpieces: Image Completion with Context-Adaptive Diffusion
ConFill modifies diffusion sampling with a context-adaptive Wasserstein-type discrepancy and complexity-based sampling, reporting improved FID, LPIPS, and SSIM on image inpainting benchmarks.
-
ControlMambaIR: Conditional Controls with State-Space Model for Image Restoration
A diffusion image restoration model with a Mamba condition network reports low LPIPS/FID on several benchmarks, but the PSNR losses and internal inconsistencies undermine the stated performance claims.
-
Shaping Inductive Bias in Diffusion Models through Frequency-Based Noise Control
Frequency-filtered noise in the diffusion forward process steers what the denoiser learns, yielding modest FID gains on some datasets and partial recovery after known-band corruption.
-
Efficient Continuous Video Flow Model for Video Prediction
The paper adapts the authors' prior continuous-video-process framework to latent space, reporting state-of-the-art FVD on KTH, BAIR, Human3.6M, and UCF101 with fewer parameters and sampling steps.
-
Continuous Video Process: Modeling Videos as Continuous Multi-Dimensional Processes for Video Prediction
CVP trains a network to reverse a continuous interpolation between past and future frames, reporting competitive FVD scores and 25-step sampling on KTH, BAIR, Human3.6M, and UCF101.
Discussion (0). Continue with ORCID to comment.