Pith. sign in

REVIEW 4 cited by

DreamSampler: Unifying Diffusion Sampling and Score Distillation for Image Manipulation

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 2403.11415 v2 pith:727QJSIZ submitted 2024-03-18 cs.CV cs.AIcs.LG

Jeongsol Kim , Geon Yeong Park , Jong Chul Ye This is my paper · ORCID
classification cs.CVcs.AIcs.LG
keywords dreamsamplerimagesamplingapproachesdiffusiondistillationreverseapproach
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Reverse sampling and score-distillation have emerged as main workhorses in recent years for image manipulation using latent diffusion models (LDMs). While reverse diffusion sampling often requires adjustments of LDM architecture or feature engineering, score distillation offers a simple yet powerful model-agnostic approach, but it is often prone to mode-collapsing. To address these limitations and leverage the strengths of both approaches, here we introduce a novel framework called {\em DreamSampler}, which seamlessly integrates these two distinct approaches through the lens of regularized latent optimization. Similar to score-distillation, DreamSampler is a model-agnostic approach applicable to any LDM architecture, but it allows both distillation and reverse sampling with additional guidance for image editing and reconstruction. Through experiments involving image editing, SVG reconstruction and etc, we demonstrate the competitive performance of DreamSampler compared to existing approaches, while providing new applications. Code: https://github.com/DreamSampler/dream-sampler

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

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

  1. InverseCrafter: Efficient Video ReCapture as a Latent Domain Inverse Problem

    cs.CV 2025-12 conditional novelty 6.0 of 10

    A training-free, near-zero-overhead inverse solver for novel-view video generation and inpainting that projects masks into continuous multi-channel latent masks and applies DDS with conjugate gradient in latent space.

  2. Inference-Time Diffusion Model Distillation

    cs.CV 2024-12 conditional novelty 6.0 of 10

    Distillation++ refines the first denoising steps of distilled diffusion models by interpolating student estimates with teacher model estimates, improving FID and text alignment on several SDXL-based few-step baselines.

  3. Optical-Flow Guided Prompt Optimization for Coherent Video Generation

    cs.CV 2024-11 conditional novelty 6.0 of 10

    MotionPrompt improves temporal consistency in text-to-video diffusion models by optimizing learnable prompt tokens during sampling, guided by an optical-flow discriminator.

  4. FlowAlign: Trajectory-Regularized, Inversion-Free Flow-based Image Editing

    cs.CV 2025-05 conditional novelty 5.0 of 10

    FlowAlign adds a terminal-point source-similarity regularization to inversion-free flow-based editing, improving structural consistency while maintaining semantic alignment.

Pith tools