Pith. sign in

REVIEW 10 cited by

Training-free Diffusion Acceleration with Bottleneck Sampling

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

arxiv 2503.18940 v2 pith:ZTA4WRUL submitted 2025-03-24 cs.CV

classification cs.CV
keywords samplingbottleneckgenerationwhilecomputationaldenoisingdiffusionimage
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
abstract

Diffusion models have demonstrated remarkable capabilities in visual content generation but remain challenging to deploy due to their high computational cost during inference. This computational burden primarily arises from the quadratic complexity of self-attention with respect to image or video resolution. While existing acceleration methods often compromise output quality or necessitate costly retraining, we observe that most diffusion models are pre-trained at lower resolutions, presenting an opportunity to exploit these low-resolution priors for more efficient inference without degrading performance. In this work, we introduce Bottleneck Sampling, a training-free framework that leverages low-resolution priors to reduce computational overhead while preserving output fidelity. Bottleneck Sampling follows a high-low-high denoising workflow: it performs high-resolution denoising in the initial and final stages while operating at lower resolutions in intermediate steps. To mitigate aliasing and blurring artifacts, we further refine the resolution transition points and adaptively shift the denoising timesteps at each stage. We evaluate Bottleneck Sampling on both image and video generation tasks, where extensive experiments demonstrate that it accelerates inference by up to 3$\times$ for image generation and 2.5$\times$ for video generation, all while maintaining output quality comparable to the standard full-resolution sampling process across multiple evaluation metrics.

Discussion (0). Sign in to comment.

Forward citations

Cited by 10 Pith papers

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

  1. Image Restoration via Diffusion Models with Dynamic Resolution

    cs.CV 2026-05 conditional novelty 7.0 of 10

    Dynamic resolution priors enable faster diffusion-based image restoration by operating in lower-dimensional subspaces, with adapted methods outperforming prior DM approaches on most tasks.

  2. SpecEdit: Training-Free Acceleration for Diffusion based Image Editing via Semantic Locking

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    SpecEdit accelerates diffusion-based image editing up to 10x by using a low-resolution draft to identify edit-relevant tokens via semantic discrepancies for selective high-resolution denoising.

  3. Efficient Video Diffusion Models: Advancements and Challenges

    cs.CV 2026-04 unverdicted novelty 7.0 of 10

    A survey that groups efficient video diffusion methods into four paradigms—step distillation, efficient attention, model compression, and cache/trajectory optimization—and outlines open challenges for practical use.

  4. Spectral Progressive Diffusion for Efficient Image and Video Generation

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    Spectral Progressive Diffusion accelerates image and video generation in pretrained diffusion models by progressively growing resolution along the denoising trajectory using spectral noise expansion and a power spectr...

  5. Cross-Resolution Distribution Matching for Diffusion Distillation

    cs.CV 2026-03 conditional novelty 6.0 of 10

    Cross-resolution distribution matching with logSNR timestep alignment and predicted-noise re-injection enables high-fidelity few-step multi-resolution cascaded diffusion distillation.

  6. SURF: Signature-Retained Fast Video Generation

    cs.GR 2025-11 unverdicted novelty 6.0 of 10

    SURF accelerates high-resolution video generation up to 12.5x by using noise reshifting for low-res previews from pretrained models and a shifting-window Refiner for efficient upscaling that retains original signatures.

  7. Phase-Aligned RoPE for Mixed-Resolution Diffusion Transformer

    cs.CV 2025-11 conditional novelty 6.0 of 10

    Expressing all RoPE positions on the query's grid ('one attention, one scale') plus a small boundary content-exchange step restores mixed-resolution diffusion generation that naive position interpolation destroys.

  8. Spectral Progressive Diffusion for Efficient Image and Video Generation

    cs.CV 2026-05 unverdicted novelty 5.0 of 10

    Spectral Progressive Diffusion progressively grows resolution during denoising of pretrained diffusion models via spectral noise expansion and a power-spectrum-derived schedule, enabling training-free speedups and a f...

  9. Training-free, Perceptually Consistent Low-Resolution Previews with High-Resolution Image for Efficient Workflows of Diffusion Models

    eess.IV 2026-04 unverdicted novelty 5.0 of 10

    A commutator-zero condition enables training-free generation of perceptually consistent low-resolution previews for high-resolution diffusion model outputs, achieving up to 33% computation reduction.

  10. FasterVAR: Plug-and-Play Acceleration for Visual Autoregressive Models

    cs.CV 2025-12 conditional novelty 5.0 of 10

    Stage-aware pruning of late generation steps, using random projection and cached-feature restoration, speeds up VAR text-to-image models by up to 3.4x with minimal quality loss.

Pith tools