Pith. sign in

REVIEW 1 cited by

Video Editing via Factorized Diffusion Distillation

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 2403.09334 v2 pith:STCGGSSH submitted 2024-03-14 cs.CV

Uriel Singer , Amit Zohar , Yuval Kirstain , Shelly Sheynin , Adam Polyak , Devi Parikh , Yaniv Taigman This is my paper · ORCID
classification cs.CV
keywords videoeditingadapterdistillationeditprocedureadaptersalign
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

We introduce Emu Video Edit (EVE), a model that establishes a new state-of-the art in video editing without relying on any supervised video editing data. To develop EVE we separately train an image editing adapter and a video generation adapter, and attach both to the same text-to-image model. Then, to align the adapters towards video editing we introduce a new unsupervised distillation procedure, Factorized Diffusion Distillation. This procedure distills knowledge from one or more teachers simultaneously, without any supervised data. We utilize this procedure to teach EVE to edit videos by jointly distilling knowledge to (i) precisely edit each individual frame from the image editing adapter, and (ii) ensure temporal consistency among the edited frames using the video generation adapter. Finally, to demonstrate the potential of our approach in unlocking other capabilities, we align additional combinations of adapters

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

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

  1. Beyond Generation: Unlocking Universal Editing via Self-Supervised Fine-Tuning

    cs.CV 2024-12 conditional novelty 6.0 of 10

    UES adds a self-supervised video condition to text-to-video diffusion models, enabling them to edit videos from delta prompts without paired supervision.

Pith tools