Pith. sign in

REVIEW 11 cited by

Cold Diffusion: Inverting Arbitrary Image Transforms Without Noise

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 2208.09392 v1 pith:AFNTN6HI submitted 2022-08-19 cs.CV cs.LG

Arpit Bansal , Eitan Borgnia , Hong-Min Chu , Jie S. Li , Hamid Kazemi , Furong Huang , Micah Goldblum , Jonas Geiping
show 1 more author
Tom Goldstein
This is my paper
classification cs.CVcs.LG
keywords modelsdiffusionimagegenerativenoisearbitrarychoicedegradation
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
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

Discussion (0). Sign in to comment.

Forward citations

Cited by 11 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution

    cs.CL 2023-09 unverdicted novelty 8.0 of 10

    Promptbreeder evolves both task prompts and the mutation prompts that improve them using LLMs, outperforming Chain-of-Thought and Plan-and-Solve on arithmetic and commonsense reasoning benchmarks.

  2. Building Normalizing Flows with Stochastic Interpolants

    cs.LG 2022-09 conditional novelty 8.0 of 10

    Normalizing flows are constructed by learning the velocity of a stochastic interpolant via a quadratic loss derived from its probability current, yielding an efficient ODE-based alternative to diffusion models.

  3. Decoupled Residual Denoising Diffusion Models for Unified and Data Efficient Image-to-Image Translation

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    DRDD decouples diffusion into independent noise and residual stages to preserve domain harmonization and enable unified data-efficient I2I translation.

  4. CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters

    hep-ex 2026-06 conditional novelty 6.0 of 10

    A one-step generative model for calorimeter showers, using MeanFlow, a learned Gaussian-mixture prior, and a physics-constrained loss, matches diffusion-model quality at far fewer evaluations.

  5. Progressive Checkerboards for Autoregressive Multiscale Image Generation

    cs.CV 2026-02 conditional novelty 6.0 of 10

    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.

  6. HazeMatching: Dehazing Light Microscopy Images with Guided Conditional Flow Matching

    eess.IV 2025-06 unverdicted novelty 6.0 of 10

    HazeMatching adapts conditional flow matching with hazy-image guidance to dehaze microscopy images while balancing fidelity and realism on synthetic and real data.

  7. DragNUWA: Fine-grained Control in Video Generation by Integrating Text, Image, and Trajectory

    cs.CV 2023-08 unverdicted novelty 6.0 of 10

    DragNUWA integrates text, image, and trajectory controls into a diffusion video model using a Trajectory Sampler, Multiscale Fusion, and Adaptive Training to enable fine-grained open-domain video generation.

  8. CaloTrilogy: Toward a Breakthrough in One-Step, End-to-End, Physics-Guided Shower Generation for Modern Calorimeters

    hep-ex 2026-06 unverdicted novelty 5.0 of 10

    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.

  9. DDGAD: Trajectory Dynamics for Diffusion-Based Graph Anomaly Detection

    cs.LG 2026-05 unverdicted novelty 5.0 of 10

    DDGAD detects graph anomalies via unstable diffusion trajectories arising from contamination in anomalous nodes, using reliability-aware consensus and three anomaly signals.

  10. Single Image Reflection Removal with Patch Reflectance Prior

    cs.CV 2023-12 unverdicted novelty 5.0 of 10

    Proposes a patch-based reflection intensity prior learned by RPEN and applied in PRRN transformer U-Net to achieve state-of-the-art single image reflection removal on real-world benchmarks.

  11. A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models

    cs.LG 2026-05 unverdicted novelty 4.0 of 10

    Diffusion, score-based, and flow matching models are unified as instances of learning time-dependent vector fields inducing marginal distributions governed by continuity and Fokker-Planck equations.

Pith tools