Papers › Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

Learning to Forecast and Refine Residual Motion for Image-to-Video Generation

26 Jul 2018ECCV 2018 9arXiv:1807.09951archive 2025-07-28

Long Zhao, Xi Peng, Yu Tian, Mubbasir Kapadia, Dimitris Metaxas

We consider the problem of image-to-video translation, where an input image is translated into an output video containing motions of a single object. Recent methods for such problems typically train transformation networks to generate future frames conditioned on the structure sequence. Parallel work has shown that short high-quality motions can be generated by spatiotemporal generative networks that leverage temporal knowledge from the training data. We combine the benefits of both approaches and propose a two-stage generation framework where videos are generated from structures and then refined by temporal signals. To model motions more efficiently, we train networks to learn residual motion between the current and future frames, which avoids learning motion-irrelevant details. We conduct extensive experiments on two image-to-video translation tasks: facial expression retargeting and human pose forecasting. Superior results over the state-of-the-art methods on both tasks demonstrate the effectiveness of our approach.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

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

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: community (archive-listed): 15 samples from 1 repository, 12 ran (12 with no instrument failure; 0 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-25 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

garyzhao/FRGAN mentioned on GitHubpytorchApache-2.0Syntology: 15 samples, 12 ran (0 instrument-failed) · 3 unverified 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: 12 ran (of which 0 constructed an object rather than computing a result; 12 with no instrument failure: 0 honoured, 0 violated, 12 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

12ran
3unverified

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 garyzhao/FRGAN. “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. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (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 are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. 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 six 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; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. 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.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

garyzhao/FRGAN community (archive-listed) 15 samples, 12 ran (0 instrument-failed) · 3 unverified
add_sn common/utils.py ran Apache-2.0 (permissive) · 8df37ce3b5bac7f3 · report fixture: signature m:callable/0/? · returned SimpleConvModel · level recorded 2026-09-26
compute_bbox_size dfa/face.py ran fingerprinted Apache-2.0 (permissive) · caf28d4f019dee35 · report fixture: signature pts:ndarray/2/float · returned float · level recorded 2026-09-26
crop_img in 12 papers dfa/face.py ran Apache-2.0 (permissive) · b228caa6744033c7 · report fixture: signature img:ndarray/3/int, roi_box:list/1/float · returned ndarray · level recorded 2026-09-26
load_dataset_split common/io.py ran Apache-2.0 (permissive) · 685fda3ca7f39c7b · report fixture: signature data_fp:str/0/str · returned dict · level recorded 2026-09-26
loss_norm_l1 common/utils.py ran fingerprinted Apache-2.0 (permissive) · 7ae9c8bee34b0711 · report fixture: signature a:Tensor/2/float · returned Tensor · level recorded 2026-09-26
mobilenet in 10 papers dfa/mobilenet_v1.py ran Apache-2.0 (permissive) · 0e9607194d198cdc · report fixture: signature widen_factor:float/0/float, num_classes:int/0/int · returned MobileNet · level recorded 2026-09-26
mobilenet_1 dfa/mobilenet_v1.py ran Apache-2.0 (permissive) · 2e691025cd2d1017 · report fixture: signature num_classes:int/0/int, input_channel:int/0/int · returned MobileNet · level recorded 2026-09-25
mobilenet_2 dfa/mobilenet_v1.py ran Apache-2.0 (permissive) · d3aea641fac06744 · report fixture: signature num_classes:int/0/int, input_channel:int/0/int · returned MobileNet · level recorded 2026-09-25
pil_load_image common/io.py ran Apache-2.0 (permissive) · f3b964c1506b9216 · report fixture: signature img_path:str/0/str · returned Image · level recorded 2026-09-26
plot_overlap in 37 papers common/logger.py ran Apache-2.0 (permissive) · 921113cf2a16c965 · report fixture: signature logger:MockLogger/0/?, names:NoneType/0/? · returned list · level recorded 2026-09-25
torch_to_pil_image common/io.py ran Apache-2.0 (permissive) · fd56da3a7da6c57e · report fixture: signature x:Tensor/4/float · returned Image · level recorded 2026-09-26
visualize_norm common/utils.py ran fingerprinted Apache-2.0 (permissive) · e8920dc9bd595394 · report fixture: signature norm:ndarray/3/float · returned ndarray · level recorded 2026-09-26
parse_param dfa/inference.py unverified Apache-2.0 (permissive) · b14f92d78ef0a0f2 · report
predict_vertices dfa/inference.py unverified Apache-2.0 (permissive) · 1f60ac47d218051a · report
reconstruct_vertex dfa/inference.py unverified Apache-2.0 (permissive) · d8f125be3a977929 · report

Tasks

Human Pose ForecastingImage to Video GenerationTranslationVideo Generation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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