Papers › Curvature-guided dynamic scale networks for Multi-view Stereo

Curvature-guided dynamic scale networks for Multi-view Stereo

11 Dec 2021ICLR 2022 4arXiv:2112.05999archive 2025-07-28

Khang Truong Giang, Soohwan Song, Sungho Jo

Multi-view stereo (MVS) is a crucial task for precise 3D reconstruction. Most recent studies tried to improve the performance of matching cost volume in MVS by designing aggregated 3D cost volumes and their regularization. This paper focuses on learning a robust feature extraction network to enhance the performance of matching costs without heavy computation in the other steps. In particular, we present a dynamic scale feature extraction network, namely, CDSFNet. It is composed of multiple novel convolution layers, each of which can select a proper patch scale for each pixel guided by the normal curvature of the image surface. As a result, CDFSNet can estimate the optimal patch scales to learn discriminative features for accurate matching computation between reference and source images. By combining the robust extracted features with an appropriate cost formulation strategy, our resulting MVS architecture can estimate depth maps more precisely. Extensive experiments showed that the proposed method outperforms other state-of-the-art methods on complex outdoor scenes. It significantly improves the completeness of reconstructed models. As a result, the method can process higher resolution inputs within faster run-time and lower memory than other MVS methods. Our source code is available at url{https://github.com/TruongKhang/cds-mvsnet}.

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 18 code samples harvested from 1 repository linked to this paper: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 18 samples from 1 repository, 16 ran (10 with no instrument failure; 6 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.

truongkhang/cds-mvsnet officialmentioned in papermentioned on GitHubpytorchSyntology: 18 samples, 16 ran (6 instrument-failed) · 2 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

18 samples harvested: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 2 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
4ran · our draft was wrong
2ran; the contract check could not run
8ran
2unverified

Licence: 18 of the 18 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 truongkhang/cds-mvsnet. “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 2 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.

truongkhang/cds-mvsnet official repository 18 samples, 16 ran (6 instrument-failed) · 2 unverified
Conv2d in 43 papers
census: 7 implementations from 7 papers, 6 distinct outputs on one shared input
models/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 3bc61cf3e881f9be · report fixture: returned Conv2d · level recorded 2026-09-22
Conv3d models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 05f86f607ada271f · report fixture: returned Conv3d · level recorded 2026-09-22
ConvBnReLU models/model.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · b5fca0e98890a032 · report fixture: returned ConvBnReLU · level recorded 2026-09-22
CostRegNet models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · d66b6c418666bbc2 · report fixture: returned CostRegNet · level recorded 2026-09-22
Deconv3d models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · bce6b5b0519d5833 · report fixture: returned Deconv3d · level recorded 2026-09-22
DynamicConv models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 79a8f181c7eaab1f · report fixture: returned DynamicConv · level recorded 2026-09-22
FeatureNet in 7 papers models/model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 28f4a40ebb7084cc · report fixture: returned FeatureNet · level recorded 2026-09-22
Refinement models/model.py ran no licence file found · pointer only · 4b7cefd77d316e2d · report fixture: signature img:Tensor/4/float, depth_0:Tensor/4/float, depth_min:Tensor/1/float, depth_max:Tensor/1/float · returned Tensor · level recorded 2026-09-24
compute_Fmatrix models/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 86d6a76e7c4f3c07 · report fixture: signature cam_params1:Tensor/4/float, cam_params2:Tensor/4/float · returned Tensor · level recorded 2026-09-22
compute_epipole models/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 21cede8a759f4032 · report fixture: signature Fmatrix:Tensor/3/float · returned Tensor · level recorded 2026-09-22
conf_regression models/model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 1cd35a359592fa24 · report fixture: signature p:Tensor/4/float, n:int/0/int · returned Tensor · level recorded 2026-09-22
depth_regression in 8 papers models/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 16a0f9b77eb60de7 · report fixture: signature p:Tensor/4/float, depth_values:Tensor/1/float · returned Tensor · level recorded 2026-09-22
get_cur_depth_range_samples models/model.py ran · our draft was wrong no licence file found · pointer only · 792db12f794882a3 · report fixture: signature cur_depth:Tensor/3/float, ndepth:int/0/int, depth_inteval_pixel:float/0/float, shape:tuple/1/int, max_depth:float/0/float, min_depth:float/0/float · returned Tensor · level recorded 2026-09-22
get_depth_range_samples models/model.py ran · our draft was wrong no licence file found · pointer only · 3ecacc918761bd98 · report fixture: signature cur_depth:Tensor/2/float, ndepth:int/0/int, depth_inteval_pixel:float/0/float, device:str/0/str, dtype:dtype/0/?, shape:tuple/1/int, max_depth:float/0/float, min_depth:float/0/float · returned Tensor · level recorded 2026-09-22
homo_warping_3D models/model.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 5ff618caea5efc6e · 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 2026-09-22
skew_matrix models/model.py ran · honoured contract fingerprinted no licence file found · pointer only · 40437be5aba7fbca · report fixture: signature vector3d:Tensor/2/float · returned Tensor · level recorded 2026-09-22
CDSMVSNet models/model.py unverified no licence file found · pointer only · de7c585c958a9c81 · report
StageNet models/model.py unverified no licence file found · pointer only · ae54777a9917cc69 · 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 CDSFNet (graph method: CDSFNet). 20 bricks; individually on a fixture: 16 ran (of which 7 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 6 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

  1. CDSMVSNet entry · level 0 · unverified · de7c585c958a9c81
  2. CostRegNet model · level 1 · ran · d66b6c418666bbc2
  3. FeatureNet model · level 1 · ran · 28f4a40ebb7084cc
  4. Refinement model · level 1 · ran · 4b7cefd77d316e2d
  5. StageNet helper · level 0 · unverified · ae54777a9917cc69
  6. compute_Fmatrix helper · level 1 · ran; the contract check could not run (RAISES) · 86d6a76e7c4f3c07
  7. compute_epipole helper · level 1 · ran · our draft was wrong · 21cede8a759f4032
  8. get_depth_range_samples helper · level 1 · ran · our draft was wrong · 3ecacc918761bd98
  9. Conv3d helper · level 1 · ran · 05f86f607ada271f
  10. Deconv3d helper · level 1 · ran · bce6b5b0519d5833
  11. Conv2d helper · level 1 · ran · 3bc61cf3e881f9be
  12. DynamicConv helper · level 1 · ran · 79a8f181c7eaab1f
  13. ConvBnReLU helper · level 1 · ran · b5fca0e98890a032
  14. conf_regression helper · level 1 · ran · our draft was wrong · 1cd35a359592fa24
  15. depth_regression helper · level 1 · ran · honoured contract · 16a0f9b77eb60de7
  16. homo_warping_3D helper · level 1 · ran; the contract check could not run (RAISES) · 5ff618caea5efc6e
  17. skew_matrix helper · level 1 · ran · honoured contract · 40437be5aba7fbca
  18. get_cur_depth_range_samples helper · level 1 · ran · our draft was wrong · 792db12f794882a3
  19. init_bn helper · level 0 · unverified · e59939cd1cb63bd9
  20. init_uniform helper · level 0 · unverified · a3982dbf26fc8521

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="2112.05999") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

3D ReconstructionDepth EstimationPoint Clouds

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction DTU CDS-MVSNet Acc 0.351 #10 of 24 Archive leaderboard report
3D Reconstruction DTU CDS-MVSNet Comp 0.278 #10 of 24 Archive leaderboard report
3D Reconstruction DTU CDS-MVSNet Overall 0.315 #10 of 24 Archive leaderboard report
Point Clouds Tanks and Temples CDS-MVSNet Mean F1 (Intermediate) 61.58 #15 of 21 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.

Methods

Convolution

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