Papers › MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
MEMFOF: High-Resolution Training for Memory-Efficient Multi-Frame Optical Flow Estimation
Vladislav Bargatin, Egor Chistov, Alexander Yakovenko, Dmitriy Vatolin
Recent advances in optical flow estimation have prioritized accuracy at the cost of growing GPU memory consumption, particularly for high-resolution (FullHD) inputs. We introduce MEMFOF, a memory-efficient multi-frame optical flow method that identifies a favorable trade-off between multi-frame estimation and GPU memory usage. Notably, MEMFOF requires only 2.09 GB of GPU memory at runtime for 1080p inputs, and 28.5 GB during training, which uniquely positions our method to be trained at native 1080p without the need for cropping or downsampling. We systematically revisit design choices from RAFT-like architectures, integrating reduced correlation volumes and high-resolution training protocols alongside multi-frame estimation, to achieve state-of-the-art performance across multiple benchmarks while substantially reducing memory overhead. Our method outperforms more resource-intensive alternatives in both accuracy and runtime efficiency, validating its robustness for flow estimation at high resolutions. At the time of submission, our method ranks first on the Spring benchmark with a 1-pixel (1px) outlier rate of 3.289, leads Sintel (clean) with an endpoint error (EPE) of 0.963, and achieves the best Fl-all error on KITTI-2015 at 2.94%. The code is available at https://github.com/msu-video-group/memfof.
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):
get_harvested_code_for_paper(arxiv_id="2506.23151")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="2506.23151", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="2506.23151")
Code
Syntology 13 code samples harvested from 1 repository linked to this paper: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; failures of Syntology's instrument, not of the code.
By repository: official repository: 13 samples from 1 repository, 9 ran (8 with no instrument failure; 1 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 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
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
13 samples harvested: 9 ran (of which 7 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 1 where Syntology's instrument failed) · 4 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.
Licence: 0 of the 13 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 msu-video-group/memfof. “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”. For 2 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.
167a7e8bc140806b · report
fixture: signature attn:Tensor/4/float, fmap:Tensor/4/float · returned Tensor · level recorded 2026-09-24 census: 13 implementations from 12 papers, 10 distinct outputs across 4 buckets, one shared input per bucket memfof/model.py ran BSD-3-Clause (permissive) ·
14f1b0e4c1e457ba · report
fixture: returned Attention · level recorded 2026-09-22 2133e755baf0eebe · report
fixture: returned BasicMotionEncoder · level recorded 2026-09-22 5889efba95f106e9 · report
fixture: returned ConvNextBlock · level recorded 2026-09-22 aafc690578a6d225 · report
fixture: returned CorrBlock · level recorded 2026-09-22 ff47f683000643e1 · report
fixture: returned GMAUpdateBlock · level recorded 2026-09-22 0fac8348cbeeb2ca · report
fixture: returned InputPadder · level recorded 2026-09-22 4913dffc8eae9dc0 · report
fixture: returned ResNetFPN16x · level recorded 2026-09-22 7599edadbb4f2bdc · report
fixture: signature in_planes:int/0/int, out_planes:int/0/int, stride:int/0/int · returned Conv2d · level recorded 2026-09-22 0d272f32cfaeb750 · report
Method as code Syntology
What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it.
1 assembly on this paper: 1 harvested, 0 generated.
harvested Assembly for MEMFOF (graph method: MEMFOF). 15 bricks; individually on a fixture: 11 ran (of which 8 constructed an object rather than computing a result; 10 with no instrument failure: 1 honoured, 0 violated, 9 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
- MEMFOF entry · level 0 · unverified ·
3a95acdcbffbcf5b - Attention helper · level 1 · ran ·
14f1b0e4c1e457ba - CorrBlock model · level 1 · ran ·
aafc690578a6d225 - GMAUpdateBlock helper · level 1 · ran ·
ff47f683000643e1 - InputPadder helper · level 1 · ran ·
0fac8348cbeeb2ca - ResNetFPN16x helper · level 1 · ran ·
4913dffc8eae9dc0 - conv3x3 helper · level 1 · ran · our draft was wrong ·
7599edadbb4f2bdc - coords_grid helper · level 1 · ran · honoured contract ·
63d12d2090a905d4 - bilinear_sampler helper · level 0 · unverified ·
0d272f32cfaeb750 - Aggregate helper · level 1 · ran ·
167a7e8bc140806b - BasicMotionEncoder helper · level 1 · ran ·
2133e755baf0eebe - ConvNextBlock helper · level 1 · ran ·
5889efba95f106e9 - init_conv1_weights helper · level 0 · unverified ·
3eac67065d155459 - init_model_weights helper · level 0 · unverified ·
a8c4a270d6812a71 - LayerNorm helper · level 1 · ran ·
c34db513de5535f1
Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2506.23151") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
1 archive task tag without a task page not shown.
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Optical Flow Estimation | KITTI 2015 | MEMFOF | Fl-all | 2.94 | #1 of 18 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 | MEMFOF | Fl-fg | 4.66 | #1 of 18 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 (train) | MEMFOF | EPE | 2.93 | #1 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 (train) | MEMFOF | F1-all | 9.93 | #1 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-clean | MEMFOF-L | Average End-Point Error | 0.963 | #1 of 29 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-final | MEMFOF-L | Average End-Point Error | 1.907 | #1 of 28 | Archive leaderboard | report |
| Optical Flow Estimation | Spring | MEMFOF | 1px total | 3.289 | #1 of 11 | Archive leaderboard | report |
Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.
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