Papers › Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

Dense Hybrid Recurrent Multi-view Stereo Net with Dynamic Consistency Checking

21 Jul 2020ECCV 2020 8arXiv:2007.10872archive 2025-07-28

Jian-Feng Yan, Zizhuang Wei, Hongwei Yi, Mingyu Ding, Runze Zhang, Yisong Chen, Guoping Wang, Yu-Wing Tai

In this paper, we propose an efficient and effective dense hybrid recurrent multi-view stereo net with dynamic consistency checking, namely D²HC-RMVSNet, for accurate dense point cloud reconstruction. Our novel hybrid recurrent multi-view stereo net consists of two core modules: 1) a light DRENet (Dense Reception Expanded) module to extract dense feature maps of original size with multi-scale context information, 2) a HU-LSTM (Hybrid U-LSTM) to regularize 3D matching volume into predicted depth map, which efficiently aggregates different scale information by coupling LSTM and U-Net architecture. To further improve the accuracy and completeness of reconstructed point clouds, we leverage a dynamic consistency checking strategy instead of prefixed parameters and strategies widely adopted in existing methods for dense point cloud reconstruction. In doing so, we dynamically aggregate geometric consistency matching error among all the views. Our method ranks 1ˢᵗ on the complex outdoor Tanks and Temples benchmark over all the methods. Extensive experiments on the in-door DTU dataset show our method exhibits competitive performance to the state-of-the-art method while dramatically reduces memory consumption, which costs only 19.4% of R-MVSNet memory consumption. The codebase is available at https://github.com/yhw-yhw/D2HC-RMVSNet.

PaperPDFConference PDFCodeCode Syntology ran

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 33 code samples harvested from 2 repositories linked to this paper: 26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 samples from 1 repository, 14 ran (12 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 18 samples from 1 repository, 12 ran (10 with no instrument failure; 2 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

yhw-yhw/D2HC-RMVSNet officialmentioned in papermentioned on GitHubtfMITSyntology: 15 samples, 14 ran (2 instrument-failed) · 1 unverified report
haibao637/D2HC-RMVSNet mentioned on GitHubtfMITSyntology: 18 samples, 12 ran (2 instrument-failed) · 6 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

33 samples harvested: 26 ran (of which 0 constructed an object rather than computing a result; 22 with no instrument failure: 2 honoured, 0 violated, 20 with no contract checked; 4 where Syntology's instrument failed) · 7 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
4ran · our draft was wrong
20ran
7unverified

Licence: 1 of the 33 samples is pointer only, meaning Syntology does not serve that copy's text. For that sample, 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 2 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “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”. “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.

yhw-yhw/D2HC-RMVSNet official repository 15 samples, 14 ran (2 instrument-failed) · 1 unverified
conv in 178 papers models/submodule.py ran MIT (permissive) · 57f8bde36807b129 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, bias:bool/0/bool · returned Sequential · level recorded 2026-09-25
convbn in 26 papers models/submodule.py ran MIT (permissive) · ebeb960f39a49a1f · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, bias:bool/0/bool · returned Sequential · level recorded 2026-09-25
convgnrelu models/submodule.py ran MIT (permissive) · e23d1383c35bf5b7 · report fixture: signature in_channels:int/0/int, out_channels:int/0/int, kernel_size:int/0/int, stride:int/0/int, dilation:int/0/int, bias:bool/0/bool, group_channel:int/0/int · returned Sequential · level recorded 2026-09-24
get_propability_map models/vamvsnet.py ran MIT (permissive) · 6b612d536ecaad39 · report fixture: signature prob_volume:Tensor/4/float, depth:Tensor/3/float, depth_values:Tensor/3/float · returned Tensor · level recorded 2026-09-25
homo_warping in 12 papers models/module.py ran MIT (permissive) · 97a56271be444a38 · report fixture: signature src_fea:Tensor/4/float, src_proj:Tensor/3/float, ref_proj:Tensor/3/float, depth_values:Tensor/2/float · returned Tensor · level recorded 2026-09-25
homo_warping_depthwise models/module.py ran MIT (permissive) · 31cdec41e4c82500 · report fixture: signature src_fea:Tensor/4/float, src_proj:Tensor/3/float, ref_proj:Tensor/3/float, depth_value:Tensor/1/float · returned Tensor · level recorded 2026-09-25
make_nograd_func in 17 papers utils.py ran · our draft was wrong MIT (permissive) · a76fc7fb6958f97c · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
make_recursive_func in 15 papers utils.py ran · our draft was wrong MIT (permissive) · b62bec09ceeaca79 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
mvsnet_loss models/vamvsnet.py ran fingerprinted MIT (permissive) · 50fac0e8112069d0 · report fixture: signature depth_est:Tensor/3/float, depth_gt:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
mvsnet_loss_l1norm models/vamvsnet.py ran fingerprinted MIT (permissive) · 9c2943933ea1a82e · report fixture: signature depth_est:Tensor/3/float, depth_gt:Tensor/3/float, mask:Tensor/3/float · returned Tensor · level recorded 2026-09-25
read_camera_parameters in 7 papers fusion.py ran MIT (permissive) · 681f7cd39c206d61 · report fixture: signature filename:str/0/str, scale:float/0/float, index:float/0/float, flag:int/0/int · returned tuple · level recorded 2026-09-25
read_img in 41 papers fusion.py ran · honoured contract MIT (permissive) · a1db096963f65ed2 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
read_mask in 5 papers fusion.py ran MIT (permissive) · 5dc8398ed1ff8701 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-25
reduce_scalar_outputs utils.py ran MIT (permissive) · c84727567da9be2b · report fixture: signature scalar_outputs:dict/0/? · returned dict · level recorded 2026-09-25
homo_warping_depthwise_ori models/module.py unverified MIT (permissive) · 8c215efdfa14a940 · report
haibao637/D2HC-RMVSNet community (archive-listed) 18 samples, 12 ran (2 instrument-failed) · 6 unverified
center_image mvsnet/dataset.py ran fingerprinted MIT (permissive) · fb6a94f3be766ec1 · report fixture: signature img:ndarray/3/int · returned ndarray · level recorded 2026-09-25
crop in 99 papers
census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket
mvsnet/dataset.py ran MIT (permissive) · 8542218e64194c0f · report fixture: signature image:ndarray/3/float, cams:list/1/NoneType, max_h:int/0/int, max_w:int/0/int · returned tuple · level recorded 2026-09-24
get_knn_3d mvsnet/utils.py ran MIT (permissive) · ed08fe74ba4859e3 · report fixture: signature xyz:EagerTensor/5/float, shape:tuple/1/int, kernel_size:int/0/int, knn:int/0/int · returned EagerTensor · level recorded 2026-09-24
knn in 87 papers
census: 12 implementations from 17 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
mvsnet/utils.py ran MIT (permissive) · fea0b2409287c761 · report fixture: signature adj_matrix:EagerTensor/3/float, k:int/0/int · returned EagerTensor · level recorded 2026-09-24
layer in 12 papers cnn_wrapper/network.py ran MIT (permissive) · 664f1649e11743ea · report fixture: signature op:callable/0/? · returned function · level recorded 2026-09-25
less_one_percentage mvsnet/loss.py ran MIT (permissive) · 21691dc956884a92 · report fixture: signature y_true:EagerTensor/4/float, y_pred:EagerTensor/4/float, interval:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
less_three_percentage mvsnet/loss.py ran MIT (permissive) · 6f4c635649523f09 · report fixture: signature y_true:EagerTensor/4/float, y_pred:EagerTensor/4/float, interval:EagerTensor/0/float · returned EagerTensor · level recorded 2026-09-24
load_cam mvsnet/dataset.py ran MIT (permissive) · 6830d06d246cc3e7 · report fixture: signature file:StringIO/0/?, interval_scale:int/0/int · returned ndarray · level recorded 2026-09-24
non_zero_mean_absolute_diff mvsnet/loss.py ran MIT (permissive) · 5c36c6f46f8628bd · report fixture: signature y_true:EagerTensor/4/float, y_pred:EagerTensor/4/float, interval:EagerTensor/1/float · returned EagerTensor · level recorded 2026-09-24
read_cameras_binary in 40 papers mvsnet/colmap2mvsnet.py ran · our draft was wrong MIT (permissive) · 0bf4b207ce0d106a · report fixture: signature path_to_model_file:str/0/str · returned dict · level recorded 2026-09-22
read_cameras_text in 40 papers mvsnet/colmap2mvsnet.py ran · our draft was wrong MIT (permissive) · 8a38e306ff4c5b42 · report fixture: signature path:str/0/str · returned dict · level recorded 2026-09-22
read_next_bytes in 73 papers mvsnet/colmap2mvsnet.py ran · honoured contract MIT (permissive) · 56858e04e6fdb2ff · report fixture: signature fid:BytesIO/0/?, num_bytes:int/0/int, format_char_sequence:str/0/str, endian_character:str/0/str · returned tuple · level recorded 2026-09-22
PQ mvsnet/homography_warping.py unverified MIT (permissive) · c41b40eafbf6e881 · report
get_homography mvsnet/homography_warping.py unverified MIT (permissive) · dc432dc54a530ceb · report
grad_d mvsnet/homography_warping.py unverified MIT (permissive) · 39256ffa5e435bee · report
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
mvsnet/utils.py unverified MIT (permissive) here; the stored copy is pointer only · 3d90b05b13b0c0b9 · report
read_gipuma_dmb in 6 papers mvsnet/depthfusion.py unverified MIT (permissive) · f6147a9b9d73ca5e · report
scale_camera mvsnet/preprocess.py unverified MIT (permissive) · 234f6f5aa22f6f5c · report

Tasks

Point cloud reconstruction

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Concatenated Skip ConnectionConvolutionLSTMMax PoolingReLUSigmoid ActivationTanh ActivationU-Net

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