Papers › Hierarchical Discrete Distribution Decomposition for Match Density Estimation

Hierarchical Discrete Distribution Decomposition for Match Density Estimation

15 Dec 2018CVPR 2019 6arXiv:1812.06264archive 2025-07-28

Zhichao Yin, Trevor Darrell, Fisher Yu

Explicit representations of the global match distributions of pixel-wise correspondences between pairs of images are desirable for uncertainty estimation and downstream applications. However, the computation of the match density for each pixel may be prohibitively expensive due to the large number of candidates. In this paper, we propose Hierarchical Discrete Distribution Decomposition (HD^3), a framework suitable for learning probabilistic pixel correspondences in both optical flow and stereo matching. We decompose the full match density into multiple scales hierarchically, and estimate the local matching distributions at each scale conditioned on the matching and warping at coarser scales. The local distributions can then be composed together to form the global match density. Despite its simplicity, our probabilistic method achieves state-of-the-art results for both optical flow and stereo matching on established benchmarks. We also find the estimated uncertainty is a good indication of the reliability of the predicted correspondences.

PaperPDFConference PDFCodeCode 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="1812.06264")

Code

Syntology Ran 2 of 14 code samples harvested from 2 repositories linked to this paper; 12 have no recorded run. Of those that ran: 1 ran · honoured contract; 1 ran · our draft was wrong.

By repository: official repository: 13 samples from 1 repository, 1 ran; community (archive-listed): 1 sample 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.

ucbdrive/hd3 officialmentioned in papermentioned on GitHubpytorchBSD-3-Clause report
lupvasile/hd3 mentioned on GitHubpytorch 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

14 samples harvested; 2 ran; 1 honoured the contract we drafted; 12 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
1ran · our draft was wrong
12unverified

Licence: 0 of the 14 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 2 repositories linked to this paper, official or community; each sample names its own and says which. “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.

conv3x3 ucbdrive/hd3/models/dla.py official repository ran · our draft was wrong BSD-3-Clause (permissive) · dd1114865f06f0fd · report
DLAEncoder ucbdrive/hd3/models/dla_up.py official repository unverified BSD-3-Clause (permissive) · 688f35ca9f13c689 · report
EndPointError ucbdrive/hd3/hd3losses.py official repository unverified BSD-3-Clause (permissive) · 2f8bac97f40f84b7 · report
VGGEncoder ucbdrive/hd3/models/vgg.py official repository unverified BSD-3-Clause (permissive) · 4fdf1ccac81de713 · report
cupy_kernel ucbdrive/hd3/models/correlation.py official repository unverified BSD-3-Clause (permissive) · 262657b0ce1b117c · report
density2vector ucbdrive/hd3/models/hd3_ops.py official repository unverified BSD-3-Clause (permissive) · 8f3bff158df466f7 · report
dla34 ucbdrive/hd3/models/dla.py official repository unverified BSD-3-Clause (permissive) · 782f63a5ade92085 · report
flow_error ucbdrive/hd3/utils/flowlib.py official repository unverified BSD-3-Clause (permissive) · 25417465cba28cc3 · report
flow_kitti_error ucbdrive/hd3/utils/flowlib.py official repository unverified BSD-3-Clause (permissive) · c79ac417345f891a · report
flow_warp ucbdrive/hd3/models/hd3_ops.py official repository unverified BSD-3-Clause (permissive) · 076593e69f1005ab · report
readPFM ucbdrive/hd3/utils/pfm.py official repository unverified BSD-3-Clause (permissive) · 9c71f0f578921ed1 · report
read_flow ucbdrive/hd3/utils/flowlib.py official repository unverified BSD-3-Clause (permissive) · d6e5f599346d62f8 · report
vector2density ucbdrive/hd3/models/hd3_ops.py official repository unverified BSD-3-Clause (permissive) · ea94ccf225af61f5 · report
get_target_size lupvasile/hd3/inference.py community (archive-listed) ran · honoured contract fingerprinted BSD-3-Clause (permissive) · e02bca604cfc58e7 · report

Tasks

Density EstimationOptical Flow EstimationStereo MatchingStereo Matching Hand

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Optical Flow Estimation KITTI 2015 (train) HD3 EPE 13.17 #15 of 19 Archive leaderboard report
Optical Flow Estimation KITTI 2015 (train) HD3 F1-all 24.0 #15 of 19 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