Papers › PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo

PlaneMVS: 3D Plane Reconstruction from Multi-View Stereo

22 Mar 2022CVPR 2022 1arXiv:2203.12082archive 2025-07-28

Jiachen Liu, Pan Ji, Nitin Bansal, Changjiang Cai, Qingan Yan, Xiaolei Huang, Yi Xu

We present a novel framework named PlaneMVS for 3D plane reconstruction from multiple input views with known camera poses. Most previous learning-based plane reconstruction methods reconstruct 3D planes from single images, which highly rely on single-view regression and suffer from depth scale ambiguity. In contrast, we reconstruct 3D planes with a multi-view-stereo (MVS) pipeline that takes advantage of multi-view geometry. We decouple plane reconstruction into a semantic plane detection branch and a plane MVS branch. The semantic plane detection branch is based on a single-view plane detection framework but with differences. The plane MVS branch adopts a set of slanted plane hypotheses to replace conventional depth hypotheses to perform plane sweeping strategy and finally learns pixel-level plane parameters and its planar depth map. We present how the two branches are learned in a balanced way, and propose a soft-pooling loss to associate the outputs of the two branches and make them benefit from each other. Extensive experiments on various indoor datasets show that PlaneMVS significantly outperforms state-of-the-art (SOTA) single-view plane reconstruction methods on both plane detection and 3D geometry metrics. Our method even outperforms a set of SOTA learning-based MVS methods thanks to the learned plane priors. To the best of our knowledge, this is the first work on 3D plane reconstruction within an end-to-end MVS framework. Source code: https://github.com/oppo-us-research/PlaneMVS.

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 19 code samples harvested from 1 repository linked to this paper: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 19 samples from 1 repository, 16 ran (16 with no instrument failure; 0 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 on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

oppo-us-research/planemvs officialmentioned in papermentioned on GitHubpytorchMITSyntology: 19 samples, 16 ran (0 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

19 samples harvested: 16 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 0 violated, 16 with no contract checked; 0 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 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.

16ran
3unverified

Licence: 0 of the 19 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 oppo-us-research/planemvs. “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.

oppo-us-research/planemvs official repository 19 samples, 16 ran (0 instrument-failed) · 3 unverified
clean_segmentation data_preparation/clean_seg.py ran MIT (permissive) · c511045350c22381 · report fixture: signature image:ndarray/3/float, grids:ndarray/3/float, planes:ndarray/2/float, masks:ndarray/3/float, plane_ids:ndarray/1/int, gt_depth:ndarray/2/float, planeAreaThreshold:int/0/int, planeWidthThreshold:int/0/int, depthDiffThreshold:float/0/float, validAreaThreshold:float/0/float, brightThreshold:int/0/int · returned tuple · level recorded 2026-09-24
cluster in 18 papers data_preparation/cluster.py ran fingerprinted MIT (permissive) · e69c3883b85c1033 · report fixture: signature camera_planes:ndarray/2/float, cluster_anchor_num:int/0/int · returned ndarray · level recorded 2026-09-24
get_all_7scenes_path data_preparation/generate_7scenes_data.py ran MIT (permissive) · e389daf1368730ee · report fixture: signature data_root:str/0/str, sample:int/0/int · returned tuple · level recorded 2026-09-24
get_all_tum_path data_preparation/generate_tum_data.py ran MIT (permissive) · 9729d599ce2b3570 · report fixture: signature data_root:str/0/str, sample:int/0/int · returned tuple · level recorded 2026-09-24
get_grid in 24 papers data_preparation/clean_seg.py ran MIT (permissive) · a81a95d6d05862d4 · report fixture: signature h:int/0/int, w:int/0/int · returned ndarray · level recorded 2026-09-24
get_rel_trans data_preparation/generate_7scenes_data.py ran MIT (permissive) · 458c1ecc42ef30e6 · report fixture: signature ref_pose:ndarray/2/float, src_pose:ndarray/2/float · returned float64 · level recorded 2026-09-24
kmeans_cluster data_preparation/stereo_cluters.py ran fingerprinted MIT (permissive) · 0704f949c1a27579 · report fixture: signature vectors:ndarray/2/float, cluster_anchor_num:int/0/int · returned ndarray · level recorded 2026-09-24
load_color data_preparation/generate_pixel_planar.py ran MIT (permissive) · 2015b55a787e9714 · report fixture: signature color_path:str/0/str, h:int/0/int, w:int/0/int · returned ndarray · level recorded 2026-09-24
load_depth in 15 papers data_preparation/generate_pixel_planar.py ran MIT (permissive) · 5a25f72413bb176b · report fixture: signature depth_path:str/0/str, divisor:float/0/float, h:int/0/int, w:int/0/int · returned ndarray · level recorded 2026-09-24
load_image in 273 papers data_preparation/pre_process.py ran MIT (permissive) · fafa963ecd5d41cf · report fixture: signature image_path:str/0/str, resize:tuple/1/int · returned ndarray · level recorded 2026-09-24
load_intrinsic data_preparation/generate_pixel_planar.py ran MIT (permissive) · b2225dd1ab5fd8a7 · report fixture: signature intrinsic_path:str/0/str, h:int/0/int, w:int/0/int, ori_h:int/0/int, ori_w:int/0/int · returned ndarray · level recorded 2026-09-24
load_valid_ids data_preparation/stereo_cluters.py ran MIT (permissive) · 21c717dcb6058d30 · report fixture: signature seg_path:str/0/str · returned ndarray · level recorded 2026-09-24
plane_to_depth data_preparation/clean_seg.py ran MIT (permissive) · 5ecc4b1ee40f1b3c · report fixture: signature grids:Tensor/3/float, planes:Tensor/2/float, masks:Tensor/3/float, h:int/0/int, w:int/0/int · returned Tensor · level recorded 2026-09-24
read_files in 18 papers data_preparation/split_tumrgbd.py ran MIT (permissive) · 0ec4eab464808505 · report fixture: signature stereo_file:str/0/str · returned list · level recorded 2026-09-24
read_pose data_preparation/generate_7scenes_data.py ran MIT (permissive) · 58c3e75c2c18326e · report fixture: signature pose_path:str/0/str · returned ndarray · level recorded 2026-09-24
read_rgb_mapping data_preparation/generate_tum_data.py ran MIT (permissive) · f6157f7dfc05252f · report fixture: signature data_root:str/0/str, scene:str/0/str · returned tuple · level recorded 2026-09-24
cluster_vis_3d_scatters data_preparation/stereo_cluters.py unverified MIT (permissive) · 4f1c557276c4cff2 · report
load_pose in 6 papers data_preparation/pre_process.py unverified MIT (permissive) · 85fd58a1c4771f86 · report
load_raw_seg data_preparation/pre_process.py unverified MIT (permissive) · 95474bdf353f674f · report

Tasks

3D Reconstruction3D geometry

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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