Papers › AccFlow: Backward Accumulation for Long-Range Optical Flow

AccFlow: Backward Accumulation for Long-Range Optical Flow

25 Aug 2023ICCV 2023 1arXiv:2308.13133archive 2025-07-28

Guangyang Wu, Xiaohong Liu, Kunming Luo, Xi Liu, Qingqing Zheng, Shuaicheng Liu, Xinyang Jiang, Guangtao Zhai, Wenyi Wang

Recent deep learning-based optical flow estimators have exhibited impressive performance in generating local flows between consecutive frames. However, the estimation of long-range flows between distant frames, particularly under complex object deformation and large motion occlusion, remains a challenging task. One promising solution is to accumulate local flows explicitly or implicitly to obtain the desired long-range flow. Nevertheless, the accumulation errors and flow misalignment can hinder the effectiveness of this approach. This paper proposes a novel recurrent framework called AccFlow, which recursively backward accumulates local flows using a deformable module called as AccPlus. In addition, an adaptive blending module is designed along with AccPlus to alleviate the occlusion effect by backward accumulation and rectify the accumulation error. Notably, we demonstrate the superiority of backward accumulation over conventional forward accumulation, which to the best of our knowledge has not been explicitly established before. To train and evaluate the proposed AccFlow, we have constructed a large-scale high-quality dataset named CVO, which provides ground-truth optical flow labels between adjacent and distant frames. Extensive experiments validate the effectiveness of AccFlow in handling long-range optical flow estimation. Codes are available at https://github.com/mulns/AccFlow .

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 22 code samples harvested from 1 repository linked to this paper: 19 ran (of which 6 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 3 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 22 samples from 1 repository, 19 ran (16 with no instrument failure; 3 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.

mulns/accflow officialmentioned in papermentioned on GitHubpytorchMITSyntology: 22 samples, 19 ran (3 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

22 samples harvested: 19 ran (of which 6 constructed an object rather than computing a result; 16 with no instrument failure: 2 honoured, 0 violated, 14 with no contract checked; 3 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.

2ran · honoured contract
3ran; the contract check could not run
14ran
3unverified

Licence: 2 of the 22 samples are pointer only, meaning Syntology does not serve that copy's text. For 2 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from mulns/accflow. “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 3 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.

mulns/accflow official repository 22 samples, 19 ran (3 instrument-failed) · 3 unverified
AccPlus networks/AccFlow_.py ran · metamorphic tier: deterministic MIT (permissive) · c77aa920181bdc89 · report fixture: returned AccPlus · level recorded 2026-09-22
BasicEncoder in 5 papers networks/AccFlow_.py ran · metamorphic tier: deterministic MIT (permissive) · 576b3b38aab41bd9 · report fixture: returned BasicEncoder · level recorded 2026-09-22
Blending networks/AccFlow_.py ran fingerprinted MIT (permissive) · 5480e390f26b975a · report fixture: signature f1:Tensor/4/float, f2:Tensor/4/float, emap:Tensor/4/float · returned Tensor · level recorded 2026-09-24
EPE in 8 papers networks/losses.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 6baff9bff3755d04 · report fixture: signature input_flow:Tensor/2/float, target_flow:Tensor/2/float · returned Tensor · level recorded 2026-09-22
FlowDecoder networks/AccFlow_.py ran · metamorphic tier: deterministic MIT (permissive) · 8ff75104333f9fe0 · report fixture: returned FlowDecoder · level recorded 2026-09-22
FlowEncoder networks/AccFlow_.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 87bf584d40e57b05 · report fixture: returned FlowEncoder · level recorded 2026-09-22
ResidualBlock in 100 papers networks/AccFlow_.py ran · metamorphic tier: deterministic MIT (permissive) · 84fcdc8833141dbe · report fixture: returned ResidualBlock · level recorded 2026-09-22
ZeroConv2d networks/AccFlow_.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · e5c5c487aa60bd33 · report fixture: returned ZeroConv2d · level recorded 2026-09-22
backwarp in 5 papers networks/AccFlow_.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 6e854d3d7f3980c8 · report fixture: signature image:Tensor/4/float, flow:Tensor/4/float, interp_mode:str/0/str, padding_mode:str/0/str · returned Tensor · level recorded 2026-09-22
conv in 178 papers networks/modules.py ran MIT (permissive) · 277f39f9246c0485 · report fixture: signature in_planes:int/0/int, out_planes:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int · returned Conv2d · level recorded 2026-09-24
coords_grid in 24 papers networks/utils.py ran · honoured contract MIT (permissive) here; the stored copy is pointer only · 81a137c5322b4930 · report fixture: signature batch:int/0/int, ht:int/0/int, wd:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
downflow8 networks/AccFlow_.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant MIT (permissive) · 155f17374085bd89 · report fixture: signature flow:Tensor/4/float, mode:str/0/str · returned Tensor · level recorded 2026-09-22
fetch_optimizer in 8 papers fine_tune.py ran MIT (permissive) · ae7c4400ee88b6af · report fixture: signature args:Args/0/?, model:callable/0/? · returned tuple · level recorded 2026-09-24
forward_interpolate in 5 papers networks/utils.py ran fingerprinted MIT (permissive) · f7edf6ef2466762a · report fixture: signature flow:Tensor/3/float · returned Tensor · level recorded 2026-09-24
getOcc networks/AccFlow_.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted MIT (permissive) · 2f15e505b8f9ff7b · report fixture: signature F12:Tensor/4/float, I1:Tensor/4/float, I2:Tensor/4/float, binary:bool/0/bool · returned Tensor · level recorded 2026-09-22
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
networks/losses.py ran MIT (permissive) · 7cfa1a8b7a0dd16c · report fixture: signature loss_type:str/0/str · returned L1Loss · level recorded 2026-09-24
preprocess in 284 papers
census: 11 implementations from 13 papers, 10 distinct outputs across 5 buckets, one shared input per bucket
fine_tune.py ran MIT (permissive) · bdc31782573bea88 · report fixture: signature batch:dict/0/? · returned dict · level recorded 2026-09-24
sequence_loss_acc loss.py ran MIT (permissive) · f2ea78b310d23fe1 · report fixture: signature flow_preds:list/1/Tensor, flow_gts:list/1/Tensor · returned tuple · level recorded 2026-09-24
sequence_loss_raft loss.py ran MIT (permissive) · d8d15efffe600e6f · report fixture: returned tuple · level recorded 2026-09-24
AccFlow networks/AccFlow_.py unverified MIT (permissive) · 479d06f2b314617c · report
bilinear_sampler in 23 papers networks/utils.py unverified MIT (permissive) · 0d272f32cfaeb750 · report
getOcc networks/AccFlow_.py unverified MIT (permissive) · ebd6cc10326f76f8 · 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 AccFlow (graph method: AccFlow). 11 bricks; individually on a fixture: 10 ran (of which 6 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.

  1. AccFlow entry · level 0 · unverified · 479d06f2b314617c
  2. AccPlus model · level 1 · ran · c77aa920181bdc89
  3. BasicEncoder helper · level 1 · ran · 576b3b38aab41bd9
  4. Blending model · level 1 · ran · 5480e390f26b975a
  5. FlowDecoder model · level 1 · ran · 8ff75104333f9fe0
  6. FlowEncoder model · level 1 · ran · 87bf584d40e57b05
  7. downflow8 helper · level 1 · ran; the contract check could not run (RAISES) · 155f17374085bd89
  8. getOcc helper · level 1 · ran; the contract check could not run (RAISES) · 2f15e505b8f9ff7b
  9. ZeroConv2d helper · level 1 · ran · e5c5c487aa60bd33
  10. ResidualBlock helper · level 1 · ran · 84fcdc8833141dbe
  11. backwarp helper · level 1 · ran; the contract check could not run (RAISES) · 6e854d3d7f3980c8

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="2308.13133") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Optical Flow Estimation

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