Papers › RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
RAFT: Recurrent All-Pairs Field Transforms for Optical Flow
Zachary Teed, Jia Deng
We introduce Recurrent All-Pairs Field Transforms (RAFT), a new deep network architecture for optical flow. RAFT extracts per-pixel features, builds multi-scale 4D correlation volumes for all pairs of pixels, and iteratively updates a flow field through a recurrent unit that performs lookups on the correlation volumes. RAFT achieves state-of-the-art performance. On KITTI, RAFT achieves an F1-all error of 5.10%, a 16% error reduction from the best published result (6.10%). On Sintel (final pass), RAFT obtains an end-point-error of 2.855 pixels, a 30% error reduction from the best published result (4.098 pixels). In addition, RAFT has strong cross-dataset generalization as well as high efficiency in inference time, training speed, and parameter count. Code is available at https://github.com/princeton-vl/RAFT.
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="2003.12039")
Code
Syntology Ran 40 of 66 code samples harvested from 8 repositories linked to this paper; 26 have no recorded run. Of those that ran: 3 ran · honoured contract; 10 ran · our draft was wrong; 6 ran · fixture could not drive it; 21 ran with no contract checked.
By repository: official repository: 3 samples from 1 repository, 0 ran; community (archive-listed): 62 samples from 7 repositories, 40 ran; 1 identical to code first harvested elsewhere. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.
17 repositories listed; official and paper-mentioned ones first.
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
66 samples harvested; 40 ran; 3 honoured the contract we drafted; 26 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.
Licence: 17 of the 66 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 8 repositories linked to this paper, official or community; each sample names its own and says which. Some samples are identical code Syntology first harvested from another repository; for those, this paper's copy is not located and its licence is not recorded. “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.
4cb42bca3a610fbe · report
5dd835869366517d · report
cb380d6b60e23020 · report
89caa833c87120d1 · report
269ca6f91ab3d7bf · report
073e918042b41586 · report
405f48802a21a4f4 · report
3ee0a69d26057e27 · report
c69c35f159717fe0 · report
fcdbfcdd43f23a80 · report
304e803cf619d43e · report
1603237c32f607ff · report
919b54dd2d2863a6 · report
fc85bca2cba2a282 · report
861080d22f42f5ab · report
0ba6555db6828c81 · report
be4abbbe7113e5b8 · report
c84b93ca013e3092 · report
9508f88138c92c66 · report
f6d70153459c4013 · report
b70326a63189e916 · report
b343190f1d5b6e4f · report
6152b289f1a1e079 · report
c74d5482daabe793 · report
d5720f5449ed1f1b · report
ebdde07874936e17 · report
7f388bc44b6fceae · report
9dc286722d0492ff · report
81a137c5322b4930 · report
6ab307b869a70f42 · report
1ccc23830eea2a4b · report
caa1617c550d8b47 · report
ff08a3532e36e78d · report
0aa50f8a83f710b9 · report
91dffaac445c1338 · report
71d18c7938254ec3 · report
6c521de8b851930a · report
a7aae9f6f384f21e · report
561d1e8d3102a282 · report
f265d59c1942f6bb · report
f70dd0be2dffde5d · report
5f65d2c7face3e5d · report
6faaa9eebd9890d7 · report
de07f7177a45e51f · report
6e27a7978c935cc6 · report
f8f994317c0ac6e7 · report
1ecbeae1d13a0815 · report
876f851f8a5dab7a · report
576170c699910f7c · report
1fd5a8b38dc17f33 · report
f0e19d80e6ff4884 · report
7d0bab782fa467e4 · report
c9bcaa550ff44555 · report
bd49469ee4db2086 · report
12dcf7f00f5c8dac · report
88471cb2aa391635 · report
9376ca36060a23ee · report
8f9a47ae470ac10f · report
89f3a46e1c990919 · report
c3b57af079010c83 · report
42aeb8a5f8363a5f · report
c2dbd2847d3be25c · report
eaa1e8cabf344980 · report
d0c109da15d10c46 · report
944d0ffe3613a0f3 · report
1ac8cce613d98769 · report
Tasks
Results from the paper archive 2025-07-28
| Task | Dataset | Model | Metric | Value | Rank at snapshot | Leaderboard | Report |
|---|---|---|---|---|---|---|---|
| Optical Flow Estimation | KITTI 2015 (train) | RAFT | EPE | 5.04 | #10 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | KITTI 2015 (train) | RAFT | F1-all | 17.4 | #10 of 19 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-clean | RAFT (warm-start) | Average End-Point Error | 1.609 | #11 of 29 | Archive leaderboard | report |
| Optical Flow Estimation | Sintel-final | RAFT (warm-start) | Average End-Point Error | 2.855 | #10 of 28 | Archive leaderboard | report |
| Optical Flow Estimation | Spring | RAFT | 1px total | 6.790 | #7 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