Papers › Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

Rethinking Depth Estimation for Multi-View Stereo: A Unified Representation

5 Jan 2022CVPR 2022 1arXiv:2201.01501archive 2025-07-28

Rui Peng, Rongjie Wang, Zhenyu Wang, Yawen Lai, Ronggang Wang

Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to the indirect learning cost volume, and classification methods cannot directly infer the exact depth due to its discrete prediction. In this paper, we propose a novel representation, termed Unification, to unify the advantages of regression and classification. It can directly constrain the cost volume like classification methods, but also realize the sub-pixel depth prediction like regression methods. To excavate the potential of unification, we design a new loss function named Unified Focal Loss, which is more uniform and reasonable to combat the challenge of sample imbalance. Combining these two unburdened modules, we present a coarse-to-fine framework, that we call UniMVSNet. The results of ranking first on both DTU and Tanks and Temples benchmarks verify that our model not only performs the best but also has the best generalization ability.

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 15 code samples harvested from 1 repository linked to this paper: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 2 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 15 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.

prstrive/unimvsnet officialmentioned in papermentioned on GitHubpytorchMITSyntology: 15 samples, 12 ran (2 instrument-failed) · 3 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

15 samples harvested: 12 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 2 honoured, 0 violated, 8 with no contract checked; 2 where Syntology's instrument failed) · 3 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
2ran · our draft was wrong
8ran
3unverified

Licence: 1 of the 15 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 prstrive/unimvsnet. “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.

prstrive/unimvsnet official repository 15 samples, 12 ran (2 instrument-failed) · 3 unverified
classification_loss in 9 papers loss.py ran MIT (permissive) · d2cef21715760206 · report fixture: signature prob_volume:Tensor/4/float, depth_values:Tensor/4/float, interval:Tensor/0/float, depth_gt:Tensor/3/float, mask:Tensor/3/bool, weight:float/0/float · returned Tensor · level recorded 2026-09-24
depth_regression in 8 papers networks/module.py ran · honoured contract fingerprinted MIT (permissive) here; the stored copy is pointer only · 16a0f9b77eb60de7 · report fixture: signature p:Tensor/4/float, depth_values:Tensor/1/float · returned Tensor · level recorded 2026-09-22
homo_warping in 12 papers networks/module.py ran MIT (permissive) · d44ae99590b8f9bc · 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 2026-09-24
make_recursive_func in 15 papers tools.py ran · our draft was wrong MIT (permissive) · b62bec09ceeaca79 · report fixture: signature func:callable/0/? · returned function · level recorded 2026-09-24
motion_blur datasets/blendedmvs.py ran fingerprinted MIT (permissive) · 4e30ac617a07841b · report fixture: signature img:ndarray/3/int, max_kernel_size:int/0/int · returned ndarray · level recorded 2026-09-25
mvs_loss loss.py ran MIT (permissive) · ba0d276529d1705e · report fixture: signature inputs:dict/0/?, depth_gt_ms:dict/0/?, mask_ms:dict/0/?, mode:str/0/str, dlossw:list/1/float · returned Tensor · level recorded 2026-09-24
read_camera_parameters in 7 papers filter/dypcd.py ran MIT (permissive) · 0c21ad29e1868b8e · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-25
read_img in 41 papers filter/dypcd.py ran · honoured contract MIT (permissive) · a1db096963f65ed2 · report fixture: signature filename:str/0/str · returned ndarray · level recorded 2026-09-24
read_pfm in 24 papers datasets/data_io.py ran · our draft was wrong MIT (permissive) · 6b687b02c05fe850 · report fixture: signature filename:str/0/str · returned tuple · level recorded 2026-09-25
regression_loss in 8 papers loss.py ran MIT (permissive) · af922d39413f6095 · report fixture: signature depth_est:Tensor/3/float, depth_gt:Tensor/3/float, mask:Tensor/3/bool, weight:Tensor/0/float · returned Tensor · level recorded 2026-09-24
tensor2numpy in 18 papers tools.py ran MIT (permissive) · e96100b6e68bc179 · report fixture: signature vars:dict/0/? · returned dict · level recorded 2026-09-24
winner_take_all networks/module.py ran fingerprinted MIT (permissive) · 9fccefc4e39f9a9a · report fixture: signature prob_volume:Tensor/4/float, depth_values:Tensor/4/float · returned Tensor · level recorded 2026-09-24
read_gipuma_dmb in 6 papers filter/gipuma.py unverified MIT (permissive) · f6147a9b9d73ca5e · report
read_pair_file filter/dypcd.py unverified MIT (permissive) · 54c203150cdc9211 · report
save_images in 24 papers tools.py unverified MIT (permissive) · 5c7bd35439896682 · report

Tasks

3D ReconstructionClassificationDepth EstimationDepth Predictionregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Reconstruction DTU UniMVSNet Acc 0.352 #11 of 24 Archive leaderboard report
3D Reconstruction DTU UniMVSNet Comp 0.278 #11 of 24 Archive leaderboard report
3D Reconstruction DTU UniMVSNet Overall 0.315 #11 of 24 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

Focal Loss

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