Browse State-of-the-Art › 3D Face Reconstruction
3D Face Reconstruction
83 papers with code · 9 benchmarks · 11 datasets archive 2025-07-28
3D Face Reconstruction is a computer vision task that involves creating a 3D model of a human face from a 2D image or a set of images. The goal of 3D face reconstruction is to reconstruct a digital 3D representation of a person's face, which can be used for various applications such as animation, virtual reality, and biometric identification.
( Image credit: 3DDFA_V2 )
Description from the archive archive 2025-07-28.
Benchmarks archive 2025-07-28
9 leaderboard tables shown for this task, 9 with rows (a “benchmark” on this site is a table with at least one row, as on /sota), ordered by row count. “Best model” is the first row in the archive's own order at snapshot; nothing is re-ranked here and metric direction is not recorded in the archive. PwC's Trend sparklines are not in the archive, so that column is omitted.
Syntology column: samples harvested from the paper's repositories and executed on synthesized fixtures; “ran” is not a correctness claim and does not order the table. Each line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the instrument figure counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the row's paper, the line starts with that repository's state (“official” is the archive's flag, not a verdict on who wrote the code; “community repositories only” when every sample that ran came from a community repository, “official: no sample here; runs from other or unrecorded repositories” when some came from a repository the paper names or has in its text, or from none recorded); hover it for the repositories the samples that ran came from. A dash means no Syntology record for that paper, not a recorded non-run. Each “ran” line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
Libraries
Not in the archive: the export carries no per-task library table, so there is nothing to show at snapshot 2025-07-28.
Datasets archive 2025-07-28
11 datasets whose archive record lists this task, ordered by the archive's paper count.
Subtasks archive 2025-07-28
1 subtask in the archive's task tree.
Parent tasks archive 2025-07-28
Papers archive 2025-07-28
archive papers tagged: 211 · with a code link: 83 · where Syntology ran a sample: 16 (15 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument) Syntology
Show: all tagged papersonly where code ran (16 of 211 tagged: 15 with a run with no instrument failure, 1 where every run was a failure of Syntology's instrument)
Page 1 of 3: papers 1 to 100 of 211, in archive order: by repositories listed in the archive (most first), then newest first, not by stars (the archive holds no stars, so PwC's “Social” and “Latest” sorts cannot be reproduced). Papers that list no repository come after every paper that lists one.
Papers without a page here are shown as plain text. A Syntology line reads “N ran (of which C constructed an object rather than computing a result; K with no instrument failure: H honoured, V violated, P with no contract checked; I where Syntology's instrument failed) · U unverified”; the figure “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. When the archive marks a repository official for the paper, the line starts with that repository's state (the archive's flag, not a verdict on who wrote the code); hover it for the repositories the samples that ran came from. The first sentence of the abstract is shown for the first 30 papers; every abstract is on its paper's page.
-
2 Dec 2016 110 repositories listed Syntology 103 ran (of which 45 constructed an object rather than computing a result; 74 with no instrument failure: 0 honoured, 0 violated, 74 with no contract checked; 29 where Syntology's instrument failed) · 61 unverified (of 164 harvested samples) · 92 pointer-only (licence)Point cloud is an important type of geometric data structure.
-
3 Oct 2017 19 repositories listedIt involves predicting the co-ordinates of the FKPs, e. g. nose tip, center of eyes, etc, for a given face.
-
1 Jun 2020 9 repositories listedThough tremendous strides have been made in uncontrolled face detection, accurate and efficient 2D face alignment and 3D face reconstruction in-the-wild remain an open challenge.
-
1 Nov 2017 9 repositories listedFLAME is low-dimensional but more expressive than the FaceWarehouse model and the Basel Face Model.
-
27 Sep 2016 7 repositories listed Syntology 7 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 9 harvested samples)Despite the size of the dataset, some of our models train to convergence in less than a day on a single machine using TensorFlow.
-
15 Dec 2016 5 repositories listedThe 3D shapes of faces are well known to be discriminative.
-
15 Aug 2022 4 repositories listedEven though 3D face reconstruction has achieved impressive progress, most orthogonal projection-based face reconstruction methods can not achieve accurate and consistent reconstruction results when the face is very…
-
19 Oct 2021 4 repositories listedOur synergy process leverages a representation cycle for 3DMM parameters and 3D landmarks.
-
20 Mar 2019 4 repositories listed Syntology official (archive's flag): 6 ran · 25 ran (of which 0 constructed an object rather than computing a result; 20 with no instrument failure: 3 honoured, 0 violated, 17 with no contract checked; 5 where Syntology's instrument failed) · 11 unverified (of 36 harvested samples) · 1 pointer-only (licence)Recently, deep learning based 3D face reconstruction methods have shown promising results in both quality and efficiency.
-
21 Mar 2018 4 repositories listed Syntology official (archive's flag): 8 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 10 harvested samples)We propose a straightforward method that simultaneously reconstructs the 3D facial structure and provides dense alignment.
-
21 Sep 2020 3 repositories listed Syntology official (archive's flag): 7 ran · 9 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 1 honoured, 1 violated, 3 with no contract checked; 4 where Syntology's instrument failed) · 1 unverified (of 10 harvested samples) · 7 pointer-only (licence)Firstly, on the basis of a lightweight backbone, we propose a meta-joint optimization strategy to dynamically regress a small set of 3DMM parameters, which greatly enhances speed and accuracy simultaneously.
-
12 Mar 2020 3 repositories listed Syntology official (archive's flag): 1 ran · 11 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 1 honoured, 0 violated, 7 with no contract checked; 3 where Syntology's instrument failed) · 4 unverified (of 15 harvested samples) · 2 pointer-only (licence)In this paper, we introduce a method to reconstruct 3D facial shapes with high-fidelity textures from single-view images in-the-wild, without the need to capture a large-scale face texture database.
-
1 Dec 2023 2 repositories listedIn this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL).
-
FaceDNeRF: Semantics-Driven Face Reconstruction, Prompt Editing and Relighting with Diffusion Models1 Jun 2023 2 repositories listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified (of 3 harvested samples) · 3 pointer-only (licence)The ability to create high-quality 3D faces from a single image has become increasingly important with wide applications in video conferencing, AR/VR, and advanced video editing in movie industries.
-
1 Jan 2022 2 repositories listedRemoving hair from portrait images is challenging due to the complex occlusions between hair and face, as well as the lack of paired portrait data with/without hair.
-
30 Mar 2021 2 repositories listedRecent work on Deep Learning in the area of face analysis has focused on supervised learning for specific tasks of interest (e. g. face recognition, facial landmark localization etc.)
-
7 Dec 2020 2 repositories listedSome methods produce faces that cannot be realistically animated because they do not model how wrinkles vary with expression.
-
16 May 2019 2 repositories listed Syntology 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples)The estimation of 3D face shape from a single image must be robust to variations in lighting, head pose, expression, facial hair, makeup, and occlusions.
-
22 Mar 2019 2 repositories listed3D face reconstruction from a single 2D image is a challenging problem with broad applications.
-
15 Jun 2018 2 repositories listed Syntology official (archive's flag): 2 ran · 8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 13 harvested samples)We train a regression network using these objectives, a set of unlabeled photographs, and the morphable model itself, and demonstrate state-of-the-art results.
-
29 Mar 2017 2 repositories listedIt has been recently shown that neural networks can recover the geometric structure of a face from a single given image.
-
23 May 2025 1 repository listedFurthermore, we propose a new component, namely correction, and present a computationally efficient approach that penalizes for mesh topology inconsistency.
-
1 Jan 2025 1 repository listedThese person-specific models excel at capturing individual facial shapes and detailed features while preserving the robustness and prior knowledge of detail variations from the base model.
-
21 Oct 2024 1 repository listedThis paper tries to tackle this problem by introducing a novel method for texture estimation from a single image by first using StyleGAN and 3D Morphable Models.
-
10 Oct 2024 1 repository listedThe results show that our multi-task learning approach significantly improves the loss function for delicate facial parts, thus enhancing the quality of reconstruction in these specific areas.
-
5 Apr 2024 1 repository listedInstead, SMIRK replaces the differentiable rendering with a neural rendering module that, given the rendered predicted mesh geometry, and sparsely sampled pixels of the input image, generates a face image.
-
8 Mar 2024 1 repository listedTo overcome this limitation and enhance the reconstruction of 3D structural features, we propose an innovative approach that integrates existing 2D features with 3D features to guide the model learning process.
-
18 Jan 2024 1 repository listedRecent advances in single-image 3D face reconstruction have shown remarkable progress in various applications.
-
1 Jan 2024 1 repository listedTo solve these problems we introduce an Identity-Conditioned Latent Diffusion Model for face UV-texture generation (UV-IDM) to generate photo-realistic textures based on the Basel Face Model (BFM).
-
12 Jun 2023 1 repository listedWe use raw MVS scans as supervision during training, but, once trained, TEMPEH directly predicts 3D heads in dense correspondence without requiring scans.
-
19 May 2023 1 repository listed
-
24 Apr 2023 1 repository listed
-
6 Apr 2023 1 repository listed Syntology official (archive's flag): 12 ran · 12 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified (of 12 harvested samples) · 2 pointer-only (licence)
-
28 Feb 2023 1 repository listed
-
10 Feb 2023 1 repository listed
-
25 Nov 2022 1 repository listed Syntology official (archive's flag): 3 ran · 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified (of 5 harvested samples) · 1 pointer-only (licence)
-
11 Aug 2022 1 repository listed
-
22 Jul 2022 1 repository listed
-
10 May 2022 1 repository listed
-
9 May 2022 1 repository listed
-
24 Apr 2022 1 repository listed
-
13 Apr 2022 1 repository listed
-
8 Apr 2022 1 repository listed
-
26 Mar 2022 1 repository listed Syntology official (archive's flag): 5 ran · 5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified (of 6 harvested samples) · 1 pointer-only (licence)
-
18 Mar 2022 1 repository listed
-
18 Mar 2022 1 repository listed
-
20 Feb 2022 1 repository listed
-
20 Jan 2022 1 repository listed
-
29 Dec 2021 1 repository listed
-
11 Dec 2021 1 repository listed
-
16 Nov 2021 1 repository listed
-
1 Nov 2021 1 repository listed
-
18 Jun 2021 1 repository listed Syntology 6 ran (of which 6 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 6 samples that ran constructed an object rather than computing a result (of 9 harvested samples)
-
17 Jun 2021 1 repository listed
-
6 Jun 2021 1 repository listed Syntology official (archive's flag): 6 ran · 6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 0 violated, 6 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified (of 8 harvested samples)
-
16 May 2021 1 repository listed
-
11 May 2021 1 repository listed
-
8 Apr 2021 1 repository listed
-
4 Feb 2021 1 repository listed
-
6 Jan 2021 1 repository listed
-
20 Aug 2020 1 repository listed Syntology official (archive's flag): 2 ran · 2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified (of 2 harvested samples) · 2 pointer-only (licence)
-
1 Aug 2020 1 repository listed
-
1 Aug 2020 1 repository listed
-
24 Jul 2020 1 repository listed Syntology official (archive's flag): 11 ran · 11 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 0 where Syntology's instrument failed) · 5 unverified (of 16 harvested samples)
-
1 Jun 2020 1 repository listed
-
20 Apr 2020 1 repository listed
-
30 Mar 2020 1 repository listed
-
27 Mar 2020 1 repository listed
-
21 Mar 2020 1 repository listed
-
25 Oct 2019 1 repository listed
-
3 Oct 2019 1 repository listed
-
1 Oct 2019 1 repository listed
-
30 Aug 2019 1 repository listed
-
15 Feb 2019 1 repository listed
-
13 Feb 2019 1 repository listed
-
24 Sep 2018 1 repository listed
-
16 Aug 2018 1 repository listed
-
2 Feb 2018 1 repository listed
-
14 Dec 2017 1 repository listed
-
5 Sep 2017 1 repository listed
-
22 Mar 2017 1 repository listed
-
1 Feb 2016 1 repository listed
-
13 Jan 2014 1 repository listed
-
Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction1 May 2025 0 repositories listed
-
Sketch-1-to-3: One Single Sketch to 3D Detailed Face Reconstruction25 Feb 2025 0 repositories listed
-
S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors1 Jan 2025 0 repositories listed
-
3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes25 Dec 2024 0 repositories listed
-
Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes25 Dec 2024 0 repositories listed
-
Generative Landmarks Guided Eyeglasses Removal 3D Face Reconstruction25 Dec 2024 0 repositories listed
-
3D Face Reconstruction From Radar Images3 Dec 2024 0 repositories listed
-
OFER: Occluded Face Expression Reconstruction29 Oct 2024 0 repositories listed
-
Stable Video Portraits26 Sep 2024 0 repositories listed
-
Exploring 3D Face Reconstruction and Fusion Methods for Face Verification: A Case-Study in Video Surveillance16 Sep 2024 0 repositories listed
-
VGG-Tex: A Vivid Geometry-Guided Facial Texture Estimation Model for High Fidelity Monocular 3D Face Reconstruction15 Sep 2024 0 repositories listed
-
High-Fidelity Facial Albedo Estimation via Texture Quantization19 Jun 2024 0 repositories listed
-
FaceGPT: Self-supervised Learning to Chat about 3D Human Faces11 Jun 2024 0 repositories listed
-
DNPM: A Neural Parametric Model for the Synthesis of Facial Geometric Details30 May 2024 0 repositories listed
-
FaceLift: Semi-supervised 3D Facial Landmark Localization30 May 2024 0 repositories listed
-
Monocular Identity-Conditioned Facial Reflectance Reconstruction30 Mar 2024 0 repositories listed
-
Skull-to-Face: Anatomy-Guided 3D Facial Reconstruction and Editing24 Mar 2024 0 repositories listed
Syntology lines on 16 of the papers shown; no Syntology record for the others (a paper without an arXiv id cannot be joined to the graph, and absence from the graph layer is not a recorded non-run). “Ran” means the sample executed on a synthesized fixture, not that the paper's result was reproduced; each line links to that paper's sample list. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. For agents: get_harvested_code_for_paper(arxiv_id) lists each paper's samples; how to connect.
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