Papers › FlowFormer: A Transformer Architecture for Optical Flow

FlowFormer: A Transformer Architecture for Optical Flow

30 Mar 2022arXiv:2203.16194archive 2025-07-28

Zhaoyang Huang, Xiaoyu Shi, Chao Zhang, Qiang Wang, Ka Chun Cheung, Hongwei Qin, Jifeng Dai, Hongsheng Li

We introduce optical Flow transFormer, dubbed as FlowFormer, a transformer-based neural network architecture for learning optical flow. FlowFormer tokenizes the 4D cost volume built from an image pair, encodes the cost tokens into a cost memory with alternate-group transformer (AGT) layers in a novel latent space, and decodes the cost memory via a recurrent transformer decoder with dynamic positional cost queries. On the Sintel benchmark, FlowFormer achieves 1.159 and 2.088 average end-point-error (AEPE) on the clean and final pass, a 16.5% and 15.5% error reduction from the best published result (1.388 and 2.47). Besides, FlowFormer also achieves strong generalization performance. Without being trained on Sintel, FlowFormer achieves 1.01 AEPE on the clean pass of Sintel training set, outperforming the best published result (1.29) by 21.7%.

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="2203.16194")

Code

Syntology Ran 1 of 7 code samples harvested from 1 repository linked to this paper; 6 have no recorded run. Of those that ran: 1 ran · honoured contract.

By repository: official repository: 7 samples from 1 repository, 1 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

drinkingcoder/FlowFormer-Official officialpytorchApache-2.0 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

7 samples harvested; 1 ran; 1 honoured the contract we drafted; 6 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 · honoured contract
6unverified

Licence: 0 of the 7 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 drinkingcoder/FlowFormer-Official. “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.

count_parameters drinkingcoder/FlowFormer-Official/train_FlowFormer.py official repository ran · honoured contract Apache-2.0 (permissive) · f6b944f50d3f15ae · report
ExpPositionEmbeddingSine drinkingcoder/FlowFormer-Official/core/FlowFormer/LatentCostFormer/attention.py official repository unverified Apache-2.0 (permissive) · 974833a610a2e3c3 · report
LinearPositionEmbeddingSine drinkingcoder/FlowFormer-Official/core/FlowFormer/LatentCostFormer/attention.py official repository unverified Apache-2.0 (permissive) · b03081b8fae36b41 · report
compute_grid_indices drinkingcoder/FlowFormer-Official/evaluate_FlowFormer_tile.py official repository unverified Apache-2.0 (permissive) · 3821d374408cdb44 · report
compute_weight drinkingcoder/FlowFormer-Official/evaluate_FlowFormer_tile.py official repository unverified Apache-2.0 (permissive) · 1f729ed0436e991f · report
nerf_encoding drinkingcoder/FlowFormer-Official/core/FlowFormer/common.py official repository unverified Apache-2.0 (permissive) · 1d30378120dbdf54 · report
validate_chairs drinkingcoder/FlowFormer-Official/evaluate_FlowFormer.py official repository unverified Apache-2.0 (permissive) · 64abef14ae987a2a · report

Tasks

DecoderOptical Flow Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 (train) FlowFormer EPE 4.09 #5 of 19 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) FlowFormer F1-all 14.7 #5 of 19 Archive leaderboard report
Optical Flow Estimation Sintel-clean FlowFormer Average End-Point Error 1.16 #5 of 29 Archive leaderboard report
Optical Flow Estimation Spring FlowFormer 1px total 6.510 #5 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