Papers › Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is...

Extrapolating and Decoupling Image-to-Video Generation Models: Motion Modeling is Easier Than You Think

2 Mar 2025CVPR 2025 1arXiv:2503.00948archive 2025-07-28

Jie Tian, Xiaoye Qu, Zhenyi Lu, Wei Wei, Sichen Liu, Yu Cheng

Image-to-Video (I2V) generation aims to synthesize a video clip according to a given image and condition (e.g., text). The key challenge of this task lies in simultaneously generating natural motions while preserving the original appearance of the images. However, current I2V diffusion models (I2V-DMs) often produce videos with limited motion degrees or exhibit uncontrollable motion that conflicts with the textual condition. To address these limitations, we propose a novel Extrapolating and Decoupling framework, which introduces model merging techniques to the I2V domain for the first time. Specifically, our framework consists of three separate stages: (1) Starting with a base I2V-DM, we explicitly inject the textual condition into the temporal module using a lightweight, learnable adapter and fine-tune the integrated model to improve motion controllability. (2) We introduce a training-free extrapolation strategy to amplify the dynamic range of the motion, effectively reversing the fine-tuning process to enhance the motion degree significantly. (3) With the above two-stage models excelling in motion controllability and degree, we decouple the relevant parameters associated with each type of motion ability and inject them into the base I2V-DM. Since the I2V-DM handles different levels of motion controllability and dynamics at various denoising time steps, we adjust the motion-aware parameters accordingly over time. Extensive qualitative and quantitative experiments have been conducted to demonstrate the superiority of our framework over existing methods.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, Syntology's MCP tool lists every function and class Syntology harvested from this paper and whether it ran (how to connect): get_harvested_code_for_paper(arxiv_id="2503.00948")

Code

Syntology Ran 6 of 15 code samples harvested from 1 repository linked to this paper; 9 have no recorded run. Of those that ran: 1 ran · violated contract; 4 ran · our draft was wrong; 1 ran with no contract checked.

By repository: official repository: 15 samples from 1 repository, 6 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Chuge0335/EDG officialmentioned on GitHubpytorchMIT report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

15 samples harvested; 6 ran; 0 honoured the contract we drafted; 9 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · violated contract
4ran · our draft was wrong
1ran
9unverified

Licence: 0 of the 15 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from Chuge0335/EDG. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself; “our draft was wrong” and “fixture could not drive it” are failures of Syntology's instrument, not of the code.

Each sample ends with its code_sha256, Syntology's identity for that exact code. An agent fetches the stored sample with Syntology's MCP tool get_code(code_sha256="…") (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples from a repository marked official are listed first. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of four reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; or the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar). Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

disabled_train Chuge0335/EDG/lvdm/basics.py official repository ran · violated contract MIT (permissive) · 4cb732f513d69dfd · report
extract_into_tensor Chuge0335/EDG/lvdm/common.py official repository ran · our draft was wrong MIT (permissive) · a15cfd7932844ef9 · report
get_obj_from_str Chuge0335/EDG/merge/model.py official repository ran · our draft was wrong MIT (permissive) · 221b2d116fdf1032 · report
load_prompts Chuge0335/EDG/evaluation/infer_multi.py official repository ran · our draft was wrong MIT (permissive) · ea66ba28a2e932e1 · report
normal_kl Chuge0335/EDG/lvdm/distributions.py official repository ran fingerprinted MIT (permissive) · 17eb0a31c91b671c · report
zero_module Chuge0335/EDG/lvdm/basics.py official repository ran · our draft was wrong MIT (permissive) · 129b804760b3115f · report
autocast Chuge0335/EDG/lvdm/common.py official repository unverified MIT (permissive) · 32af1c12fd826ef2 · report
gather_data Chuge0335/EDG/lvdm/common.py official repository unverified MIT (permissive) · b72d8eb89fd75383 · report
get_dirlist Chuge0335/EDG/evaluation/funcs.py official repository unverified MIT (permissive) · 0aa0f88278338151 · report
get_filelist Chuge0335/EDG/evaluation/funcs.py official repository unverified MIT (permissive) · 47c2ca5ed028e21d · report
get_filelist Chuge0335/EDG/evaluation/infer_multi.py official repository unverified MIT (permissive) · cd9fc7fd42461147 · report
instantiate_from_config Chuge0335/EDG/merge/model.py official repository unverified MIT (permissive) · ef52d142b2c30ac2 · report
load_model_checkpoint Chuge0335/EDG/merge/model.py official repository unverified MIT (permissive) · 579247b6fbbc2cd7 · report
load_model_checkpoint Chuge0335/EDG/evaluation/infer_multi.py official repository unverified MIT (permissive) · a9d9177dbb51afed · report
scale_module Chuge0335/EDG/lvdm/basics.py official repository unverified MIT (permissive) · 9136b5f9b735334b · report

Tasks

DenoisingImage to Video GenerationVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdapterBASECLIPDiffusion

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections