Pith. sign in

REVIEW 30 cited by

Conditional Image Generation with Score-Based Diffusion Models

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 2111.13606 v1 pith:7ATAMNLV submitted 2021-11-26 cs.LG cs.CVstat.ML

Georgios Batzolis , Jan Stanczuk , Carola-Bibiane Schönlieb , Christian Etmann This is my paper · ORCID
classification cs.LGcs.CVstat.ML
keywords diffusionconditionalmodelsscore-basedtheoreticalapproachesmulti-speedscore
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

Score-based diffusion models have emerged as one of the most promising frameworks for deep generative modelling. In this work we conduct a systematic comparison and theoretical analysis of different approaches to learning conditional probability distributions with score-based diffusion models. In particular, we prove results which provide a theoretical justification for one of the most successful estimators of the conditional score. Moreover, we introduce a multi-speed diffusion framework, which leads to a new estimator for the conditional score, performing on par with previous state-of-the-art approaches. Our theoretical and experimental findings are accompanied by an open source library MSDiff which allows for application and further research of multi-speed diffusion models.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 30 Pith papers

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

  1. Strong Gravitational Lensing Posterior Sampling in Pixel-Space Using Diffusion Models and Recurrent Inference Machines

    astro-ph.IM 2026-07 conditional novelty 7.0 of 10

    DiRIM uses a diffusion model with recurrent score refinement to sample pixel-space joint posteriors of the lensed source and foreground mass map, reproducing mock strong-lens observations to the noise level.

  2. SoK: Can Synthetic Images Replace Real Data? A Survey of Utility and Privacy of Synthetic Image Generation

    cs.CR 2025-06 conditional novelty 7.0 of 10

    A systematic survey and benchmark showing that diffusion-based synthetic data can achieve better utility-privacy tradeoffs than DP-SGD on real data for some image classifiers, with the best release strategy depending ...

  3. Using Diffusion Models to do Data Assimilation

    physics.ao-ph 2025-06 conditional novelty 7.0 of 10

    Diffusion DA systems with climatological, cycled, or forecast-augmented priors target different posterior distributions; only a per-cycle retrained model matches ensemble DA.

  4. Diffusion Models for Inverse Problems in the Exponential Family

    stat.ML 2025-02 conditional novelty 7.0 of 10

    The evidence trick approximates the likelihood score in diffusion inverse problems for exponential family observations by integrating the likelihood against a conjugate variational posterior, enabling Poisson and Bino...

  5. PriSAR: 3D Geometric-Prior-Guided Diffusion for Parameter-Controlled SAR Image Generation

    eess.IV 2026-07 conditional novelty 6.0 of 10

    A diffusion model conditioned on ray-cast point-cloud priors from 3D aircraft models generates SAR images at specified azimuth angles with higher fidelity and angle consistency than text-only baselines.

  6. Transformers with Physics-Informed Encodings and Simulation-Based Inference for Robust Detection of Eccentric Binary Black Holes in Pulsar Timing Array Data

    cs.LG 2026-07 conditional novelty 6.0 of 10

    Physics-informed Transformer encodings plus conditional normalizing flows yield sharper, better-calibrated posteriors for eccentric BBHs in white-noise PTA data than physics-agnostic SBI baselines.

  7. Structure-Semantic Co-optimized Latent Diffusion Model for Fast Visual Anagram Synthesis

    cs.CV 2026-06 conditional novelty 6.0 of 10

    S2CO-Anagram adapts multi-view parallel denoising to SDXL-Turbo with null-text structure alignment, semantic enhancement, and attention-guided noise fusion to produce superior 512x512 visual anagrams in ~2.6s.

  8. Solving Inverse Problems with Flow-based Models via Model Predictive Control

    eess.IV 2026-01 conditional novelty 6.0 of 10

    MPC-Flow applies model predictive control to guide pretrained flow models through inverse problems, with a single-step variant that avoids backpropagation and scales to 32B-parameter models on consumer hardware.

  9. An invertible generative model for forward and inverse problems

    stat.ML 2025-09 conditional novelty 6.0 of 10

    A single invertible map constructed from two triangular normalizing flows can conditionally sample both the likelihood and the posterior in Bayesian inverse problems.

  10. GEN2: A Generative Prediction-Correction Framework for Long-time Emulations of Spatially-Resolved Climate Extremes

    physics.comp-ph 2025-08 conditional novelty 6.0 of 10

    A generative Gaussian-plus-diffusion emulator trained on one CMIP6 SSP585 realization reproduces extreme temperature statistics under other emission scenarios.

  11. Probabilistic Forecasting Method for Offshore Wind Farm Cluster under Typhoon Conditions: a Score-Based Conditional Diffusion Model

    eess.SY 2025-08 conditional novelty 6.0 of 10

    A hybrid system using typhoon path embeddings and a score-based conditional diffusion model improves offshore wind power forecasting under typhoon conditions in a single real-world cluster study.

  12. Difference Inversion: Interpolate and Isolate the Difference with Token Consistency for Image Analogy Generation

    cs.CV 2025-06 conditional novelty 6.0 of 10

    Difference Inversion learns text tokens encoding the A-to-A' edit and applies those tokens to B to synthesize B' with Stable Diffusion, without model-specific tuning.

  13. Autoregressive regularized score-based diffusion models for multi-scenarios fluid flow prediction

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A regularized autoregressive score-based diffusion model predicts turbulent flows across multiple scenarios, with the variance-preserving SDE formulation performing best.

  14. ManiVideo: Generating Hand-Object Manipulation Video with Dexterous and Generalizable Grasping

    cs.CV 2024-12 conditional novelty 6.0 of 10

    ManiVideo generates bimanual hand-object manipulation videos conditioned on 3D motion sequences, using a multi-layer occlusion representation and Objaverse-based training to improve 3D consistency and object generalization.

  15. 3D-Consistent Image Inpainting with Diffusion Models

    cs.CV 2024-12 conditional novelty 6.0 of 10

    A diffusion inpainting model conditioned on a second viewpoint of the same scene produces 3D-consistent fills for occluded regions without 3D supervision.

  16. On Statistical Rates of Conditional Diffusion Transformers: Approximation, Estimation and Minimax Optimality

    stat.ML 2024-11 reject novelty 6.0 of 10

    Conditional diffusion transformers and their latent variants receive score approximation and estimation rates, but the minimax optimality headline rests on setting a derived constant equal to 1/2.

  17. SUMI: Scalable Unified Model for 3D Point Cloud Inference

    cs.CV 2026-08 conditional novelty 5.0 of 10

    SUMI refines coarse 3D point cloud predictions by injecting noisy geometric features into cross-attention, and reports state-of-the-art Chamfer distance on PCN, ShapeNet-55/34, and MVP.

  18. DECAF: De-Clustering for Adaptive Representational Unlearning

    cs.LG 2026-07 conditional novelty 5.0 of 10

    DECAF is a forget-only unlearning method that adds input noise, suppresses the forget-class probability, and diversifies outputs, achieving 0.10% forget accuracy and 79.4% retain accuracy on CIFAR-10/ResNet-18 while d...

  19. Translationese as a Rational Response to Translation Task Difficulty

    cs.CL 2026-03 unverdicted novelty 5.0 of 10

    Translationese is partly predictable from quantifiable translation-task difficulty, especially cross-lingual transfer load, more so for English-to-German than the reverse.

  20. Probabilistic Wind Power Forecasting with Tree-Based Machine Learning and Weather Ensembles

    cs.LG 2026-02 conditional novelty 5.0 of 10

    Conditional diffusion models with tree-based learners give the best probabilistic day-ahead wind power forecasts, outperforming conformalized quantile regression, natural gradient boosting, and calibrated wake models ...

  21. LSDM: LLM-Enhanced Spatio-temporal Diffusion Model for Service-Level Mobile Traffic Prediction

    cs.LG 2025-07 conditional novelty 5.0 of 10

    LSDM predicts next-hour mobile traffic per app category by feeding a diffusion model with satellite imagery, POI counts, and LLM-generated text descriptions, outperforming eight baselines on a single real-world dataset.

  22. Bidirectional Diffusion Bridge Models

    cs.CV 2025-02 conditional novelty 5.0 of 10

    BDBM uses a single masked noise-prediction network to model both forward and backward diffusion bridges between two image distributions, enabling bidirectional translation at roughly half the model cost.

  23. Generating Realistic Forehead-Creases for User Verification via Conditioned Piecewise Polynomial Curves

    cs.CV 2025-01 conditional novelty 5.0 of 10

    Geometry-driven synthetic forehead crease images improve cross-database verification when added to real training data.

  24. FlowPolicy: Enabling Fast and Robust 3D Flow-based Policy via Consistency Flow Matching for Robot Manipulation

    cs.RO 2024-12 conditional novelty 5.0 of 10

    A consistency flow matching policy conditioned on 3D point clouds generates robot actions in a single inference step, running 7x faster than DP3 with comparable success rates.

  25. Rhetorical Text-to-Image Generation via Two-layer Diffusion Policy Optimization

    cs.CV 2025-05 reject novelty 4.0 of 10

    Rhet2Pix combines staged LLM prompt decomposition with a discounted PPO fine-tuning scheme for Stable Diffusion, claiming strong rhetorical text-to-image generation, but the quantitative evidence is circular and undefined.

  26. Constraint-Aware Diffusion Guidance for Robotics: Real-Time Obstacle Avoidance for Autonomous Racing

    cs.RO 2025-05 conditional novelty 4.0 of 10

    A diffusion trajectory planner with a barrier-function guidance term and warm starting avoids obstacles in real time on a miniature race car, with 100% success in the reported trials.

  27. Fokker-Planck to Callan-Symanzik: evolution of weight matrices under training

    cs.LG 2025-01 conditional novelty 4.0 of 10

    Weight-matrix probability densities in a toy autoencoder are evolved with the Fokker-Planck equation driven by the ADAM update, and the resulting output distributions roughly match training at epoch 5.

  28. Sch\"odinger Bridge Type Diffusion Models as an Extension of Variational Autoencoders

    cs.LG 2024-12 conditional novelty 4.0 of 10

    A VAE-style derivation shows the Schrödinger bridge diffusion objective decomposes into a prior loss and a drift-matching term.

  29. Computationally Efficient Diffusion Models in Medical Imaging: A Comprehensive Review

    eess.IV 2025-05 reject novelty 3.0 of 10

    A survey of DDPM, LDM, and WDM diffusion models for medical imaging, organized around training and inference efficiency.

  30. Deep Neural Networks Inspired by Differential Equations

    cs.LG 2025-10 unverdicted

    A review of differential-equation-inspired neural networks that compiles known results into a taxonomy, with no new experiments or theory.

Pith tools