Papers › Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network

21 Mar 2018ECCV 2018 9arXiv:1803.07835archive 2025-07-28

Yao Feng, Fan Wu, Xiaohu Shao, Yan-Feng Wang, Xi Zhou

We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment. To achieve this, we design a 2D representation called UV position map which records the 3D shape of a complete face in UV space, then train a simple Convolutional Neural Network to regress it from a single 2D image. We also integrate a weight mask into the loss function during training to improve the performance of the network. Our method does not rely on any prior face model, and can reconstruct full facial geometry along with semantic meaning. Meanwhile, our network is very light-weighted and spends only 9.8ms to process an image, which is extremely faster than previous works. Experiments on multiple challenging datasets show that our method surpasses other state-of-the-art methods on both reconstruction and alignment tasks by a large margin.

PaperPDFConference PDFCodeCode Syntology ran

In Syntology View this paper on Syntology: its repositories, every harvested function with whether it ran, its licence and the call to fetch it.

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="1803.07835")

Code

Syntology Ran 0 of 10 code samples harvested from 1 repository linked to this paper; 10 have no recorded run.

By repository: official repository: 10 samples from 1 repository, 0 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

YadiraF/PRNet officialmentioned in papertfMIT report
heathentw/prnet-tf2 mentioned on GitHubtf report
jimmy0087/faceai-master mentioned on GitHubtfNOASSERTION report
minoring/PRNet mentioned on GitHubtf 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

10 samples harvested; 0 ran; 0 honoured the contract we drafted; 10 have no recorded run. Read from Syntology's graph 2026-09-25; that is when this build read the record, not when the samples ran.

10unverified

Licence: 0 of the 10 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 YadiraF/PRNet. “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.

P2sRt YadiraF/PRNet/utils/estimate_pose.py official repository unverified MIT (permissive) · 07326d46bad4e31e · report
frontalize YadiraF/PRNet/utils/rotate_vertices.py official repository unverified MIT (permissive) · 2c47072c128b71f5 · report
get_point_weight YadiraF/PRNet/utils/render.py official repository unverified MIT (permissive) · 50572306e7c01f27 · report
isPointInTri YadiraF/PRNet/utils/render.py official repository unverified MIT (permissive) · 05f23476146a0cfe · report
isRotationMatrix YadiraF/PRNet/utils/estimate_pose.py official repository unverified MIT (permissive) · 5d64cc8f381e2dbd · report
matrix2angle YadiraF/PRNet/utils/estimate_pose.py official repository unverified MIT (permissive) · b3226b96c3df432a · report
plot_kpt YadiraF/PRNet/utils/cv_plot.py official repository unverified MIT (permissive) · eb07d94367663cae · report
plot_pose_box YadiraF/PRNet/utils/cv_plot.py official repository unverified MIT (permissive) · e90ac38cb687dd7d · report
plot_vertices YadiraF/PRNet/utils/cv_plot.py official repository unverified MIT (permissive) · 273ff544685cb7f1 · report
render_texture YadiraF/PRNet/utils/render.py official repository unverified MIT (permissive) · 51145c8552370f7c · report

Tasks

3D Face ReconstructionFace AlignmentFace ModelFace Reconstructionregression

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction AFLW2000-3D PRN Mean NME 3.9625% #5 of 8 Archive leaderboard report
3D Face Reconstruction Florence PRN Mean NME 3.7551% #1 of 16 Archive leaderboard report
3D Face Reconstruction NoW Benchmark PRNet Mean Reconstruction Error (mm) 1.98 #15 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark PRNet Median Reconstruction Error 1.50 #15 of 17 Archive leaderboard report
3D Face Reconstruction NoW Benchmark PRNet Stdev Reconstruction Error (mm) 1.88 #15 of 17 Archive leaderboard report
3D Face Reconstruction REALY PRNet @cheek 1.863 (±0.698) #15 of 24 Archive leaderboard report
3D Face Reconstruction REALY PRNet @forehead 2.429 (±0.588) #15 of 24 Archive leaderboard report
3D Face Reconstruction REALY PRNet @mouth 1.838 (±0.637) #15 of 24 Archive leaderboard report
3D Face Reconstruction REALY PRNet @nose 1.923 (±0.518) #15 of 24 Archive leaderboard report
3D Face Reconstruction REALY PRNet all 2.013 #15 of 24 Archive leaderboard report
3D Face Reconstruction REALY (side-view) PRNet @cheek 1.960 (±0.731) #12 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) PRNet @forehead 2.445 (±0.570) #12 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) PRNet @mouth 1.856 (±0.607) #12 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) PRNet @nose 1.868 (±0.510) #12 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) PRNet all 2.032 #12 of 19 Archive leaderboard report
3D Face Reconstruction Stirling-HQ (FG2018 3D face reconstruction challenge) PRNet Mean Reconstruction Error (mm) 2.06 #4 of 4 Archive leaderboard report
3D Face Reconstruction Stirling-LQ (FG2018 3D face reconstruction challenge) PRNet Mean Reconstruction Error (mm) 2.38 #4 of 4 Archive leaderboard report
Face Alignment AFLW-LFPA FPN Mean NME 2.93% #1 of 3 Archive leaderboard report
Face Alignment AFLW2000-3D PRN Balanced NME (2D Sparse Alignment) 3.62% #9 of 14 Archive leaderboard report
Face Alignment AFLW2000-3D PRN Mean NME(3D Dense Alignment) 4.40% #9 of 14 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