Papers › Looking Backward: Streaming Video-to-Video Translation with Feature Banks

Looking Backward: Streaming Video-to-Video Translation with Feature Banks

24 May 2024arXiv:2405.15757archive 2025-07-28

Feng Liang, Akio Kodaira, Chenfeng Xu, Masayoshi Tomizuka, Kurt Keutzer, Diana Marculescu

This paper introduces StreamV2V, a diffusion model that achieves real-time streaming video-to-video (V2V) translation with user prompts. Unlike prior V2V methods using batches to process limited frames, we opt to process frames in a streaming fashion, to support unlimited frames. At the heart of StreamV2V lies a backward-looking principle that relates the present to the past. This is realized by maintaining a feature bank, which archives information from past frames. For incoming frames, StreamV2V extends self-attention to include banked keys and values and directly fuses similar past features into the output. The feature bank is continually updated by merging stored and new features, making it compact but informative. StreamV2V stands out for its adaptability and efficiency, seamlessly integrating with image diffusion models without fine-tuning. It can run 20 FPS on one A100 GPU, being 15x, 46x, 108x, and 158x faster than FlowVid, CoDeF, Rerender, and TokenFlow, respectively. Quantitative metrics and user studies confirm StreamV2V's exceptional ability to maintain temporal consistency.

PaperPDFCodeCode 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="2405.15757")

Code

Syntology Ran 10 of 12 code samples harvested from 1 repository linked to this paper; 2 have no recorded run. Of those that ran: 10 ran with no contract checked.

By repository: official repository: 12 samples from 1 repository, 10 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Jeff-LiangF/streamv2v officialmentioned on GitHubpytorchNOASSERTION 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

12 samples harvested; 10 ran; 0 honoured the contract we drafted; 2 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.

10ran
2unverified

Licence: 12 of the 12 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 Jeff-LiangF/streamv2v. “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.

create_onnx_path Jeff-LiangF/streamv2v/src/streamv2v/acceleration/tensorrt/builder.py official repository ran fingerprinted licence not identified · pointer only · d1f7607f85bbbcf6 · report
decode_images Jeff-LiangF/streamv2v/src/streamv2v/acceleration/tensorrt/utilities.py official repository ran licence not identified · pointer only · 16ce98a3e3130938 · report
denormalize Jeff-LiangF/streamv2v/src/streamv2v/image_utils.py official repository ran fingerprinted licence not identified · pointer only · 5dd5ccc011afb9c3 · report
get_nn_feats Jeff-LiangF/streamv2v/src/streamv2v/models/utils.py official repository ran fingerprinted licence not identified · pointer only · b2ca37137e7e5c8b · report
is_installed Jeff-LiangF/streamv2v/src/streamv2v/pip_utils.py official repository ran licence not identified · pointer only · 35d471d9e81ee42a · report
numpy_to_pil Jeff-LiangF/streamv2v/src/streamv2v/image_utils.py official repository ran licence not identified · pointer only · b188597984f52631 · report
preprocess_image Jeff-LiangF/streamv2v/src/streamv2v/acceleration/tensorrt/utilities.py official repository ran licence not identified · pointer only · 7f011624871aea53 · report
pt_to_numpy Jeff-LiangF/streamv2v/src/streamv2v/image_utils.py official repository ran licence not identified · pointer only · e0ca6f492a8f2cbf · report
random_bipartite_soft_matching Jeff-LiangF/streamv2v/src/streamv2v/models/utils.py official repository ran licence not identified · pointer only · 5537486cf51ea735 · report
version Jeff-LiangF/streamv2v/src/streamv2v/pip_utils.py official repository ran licence not identified · pointer only · 635ea667a5c67443 · report
get_nn_latent Jeff-LiangF/streamv2v/src/streamv2v/models/utils.py official repository unverified licence not identified · pointer only · ebafb3d27531a089 · report
run_python Jeff-LiangF/streamv2v/src/streamv2v/pip_utils.py official repository unverified licence not identified · pointer only · ef16b546127f1484 · report

Tasks

Translation

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

DiffusionOPT

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