Pith. sign in

REVIEW 5 cited by

Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach

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 2410.03160 v1 pith:57QXAFTS submitted 2024-10-04 cs.CV cs.LG

classification cs.CVcs.LG
keywords videogenerationdiffusionfvdmmodeltaskstemporaltimestep
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability to model complex temporal dependencies needed for various tasks like image-to-video generation. To address this limitation, we propose a frame-aware video diffusion model~(FVDM), which introduces a novel vectorized timestep variable~(VTV). Unlike conventional VDMs, our approach allows each frame to follow an independent noise schedule, enhancing the model's capacity to capture fine-grained temporal dependencies. FVDM's flexibility is demonstrated across multiple tasks, including standard video generation, image-to-video generation, video interpolation, and long video synthesis. Through a diverse set of VTV configurations, we achieve superior quality in generated videos, overcoming challenges such as catastrophic forgetting during fine-tuning and limited generalizability in zero-shot methods.Our empirical evaluations show that FVDM outperforms state-of-the-art methods in video generation quality, while also excelling in extended tasks. By addressing fundamental shortcomings in existing VDMs, FVDM sets a new paradigm in video synthesis, offering a robust framework with significant implications for generative modeling and multimedia applications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

    cs.CV 2026-05 unverdicted novelty 7.0 of 10

    Proposes V2V-Zero, a training-free framework replacing text conditioning with VLM final-layer hidden states from visual pages, achieving 0.85 on GenEval and 32.7/100 on new Simple-V2V Bench across models including vid...

  2. FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation

    cs.CV 2026-03 unverdicted novelty 7.0 of 10

    FrameDiT proposes Matrix Attention for DiTs to achieve SOTA video generation with improved temporal coherence and efficiency comparable to local factorized attention.

  3. Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm

    cs.CV 2026-05 unverdicted novelty 6.0 of 10

    V2V-Zero adapts frozen VLMs for visual conditioning via hidden states from specification pages, scoring 0.85 on GenEval and 32.7 on a new seven-task benchmark while revealing capability hierarchies in attribute bindin...

  4. INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling

    cs.CV 2026-04 unverdicted novelty 6.0 of 10

    INSPATIO-WORLD is a real-time framework for high-fidelity 4D scene generation and navigation from monocular videos via STAR architecture with implicit caching, explicit geometric constraints, and distribution-matching...

  5. Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion

    cs.CV 2025-06 unverdicted novelty 6.0 of 10

    Self Forcing trains autoregressive video diffusion models by performing autoregressive rollout with KV caching during training to close the exposure bias gap, using a holistic video-level loss and few-step diffusion f...

Pith tools