Papers › Fine-Grained Head Pose Estimation Without Keypoints

Fine-Grained Head Pose Estimation Without Keypoints

2 Oct 2017arXiv:1710.00925archive 2025-07-28

Nataniel Ruiz, Eunji Chong, James M. Rehg

Estimating the head pose of a person is a crucial problem that has a large amount of applications such as aiding in gaze estimation, modeling attention, fitting 3D models to video and performing face alignment. Traditionally head pose is computed by estimating some keypoints from the target face and solving the 2D to 3D correspondence problem with a mean human head model. We argue that this is a fragile method because it relies entirely on landmark detection performance, the extraneous head model and an ad-hoc fitting step. We present an elegant and robust way to determine pose by training a multi-loss convolutional neural network on 300W-LP, a large synthetically expanded dataset, to predict intrinsic Euler angles (yaw, pitch and roll) directly from image intensities through joint binned pose classification and regression. We present empirical tests on common in-the-wild pose benchmark datasets which show state-of-the-art results. Additionally we test our method on a dataset usually used for pose estimation using depth and start to close the gap with state-of-the-art depth pose methods. We open-source our training and testing code as well as release our pre-trained models.

PaperPDFCodeCode Syntology ran

In Syntology 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="1710.00925")

Code

Syntology Ran 3 of 3 code samples harvested from 1 repository linked to this paper; 0 have no recorded run. Of those that ran: 1 ran · honoured contract; 2 ran · our draft was wrong.

By repository: community (archive-listed): 3 samples from 1 repository, 3 ran. The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

14 repositories listed; official and paper-mentioned ones first.

natanielruiz/deep-head-pose officialmentioned in papermentioned on GitHubpytorchNOASSERTION report
chenyeheng/SmartCar mentioned on GitHubtf report
chenyeheng/SmartCar-FaceRec mentioned on GitHubtf report
yehengchen/FaceRecognition 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

3 samples harvested; 3 ran; 1 honoured the contract we drafted; 0 have no recorded run. Read from Syntology's graph 2026-09-24; that is when this build read the record, not when the samples ran.

1ran · honoured contract
2ran · our draft was wrong

Licence: 0 of the 3 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 yakhyo/head-pose-estimation. “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.

conv1x1 yakhyo/head-pose-estimation/models/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · d97ed054442099c9 · report
conv3x3 yakhyo/head-pose-estimation/models/resnet.py community (archive-listed) ran · our draft was wrong MIT (permissive) · 7f22d053fb2c79d3 · report
expand_bbox yakhyo/head-pose-estimation/onnx_inference.py community (archive-listed) ran · honoured contract fingerprinted MIT (permissive) · 0e7a40594b66badc · report

Tasks

Face AlignmentGaze EstimationHead Pose EstimationPose Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Head Pose Estimation AFLW Ruiz et al. MAE 5.324 #5 of 6 Archive leaderboard report
Head Pose Estimation AFLW2000 Hopenet Geodesic Error (GE) 9,93 #21 of 25 Archive leaderboard report
Head Pose Estimation AFLW2000 Hopenet MAE 6.15 #21 of 25 Archive leaderboard report
Head Pose Estimation AFLW2000 Multi-Loss ResNet50 (a=2) MAE 6.155 #22 of 25 Archive leaderboard report
Head Pose Estimation BIWI hopenet Geodesic Error (GE) 9.53 #18 of 29 Archive leaderboard report
Head Pose Estimation BIWI hopenet Geodesic Error - aligned (GE) 6.6 #18 of 29 Archive leaderboard report
Head Pose Estimation BIWI hopenet MAE (trained with other data) 4.89 #18 of 29 Archive leaderboard report
Head Pose Estimation BIWI hopenet MAE-aligned (trained with other data) 3.48 #18 of 29 Archive leaderboard report
Head Pose Estimation BIWI Multi-Loss ResNet50 MAE (trained with BIWI data) 4.895 #28 of 29 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

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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