Papers › 3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

3D Face Reconstruction with the Geometric Guidance of Facial Part Segmentation

1 Dec 2023CVPR 2024 1arXiv:2312.00311archive 2025-07-28

Zidu Wang, Xiangyu Zhu, Tianshuo Zhang, Baiqin Wang, Zhen Lei

3D Morphable Models (3DMMs) provide promising 3D face reconstructions in various applications. However, existing methods struggle to reconstruct faces with extreme expressions due to deficiencies in supervisory signals, such as sparse or inaccurate landmarks. Segmentation information contains effective geometric contexts for face reconstruction. Certain attempts intuitively depend on differentiable renderers to compare the rendered silhouettes of reconstruction with segmentation, which is prone to issues like local optima and gradient instability. In this paper, we fully utilize the facial part segmentation geometry by introducing Part Re-projection Distance Loss (PRDL). Specifically, PRDL transforms facial part segmentation into 2D points and re-projects the reconstruction onto the image plane. Subsequently, by introducing grid anchors and computing different statistical distances from these anchors to the point sets, PRDL establishes geometry descriptors to optimize the distribution of the point sets for face reconstruction. PRDL exhibits a clear gradient compared to the renderer-based methods and presents state-of-the-art reconstruction performance in extensive quantitative and qualitative experiments. Our project is available at https://github.com/wang-zidu/3DDFA-V3 .

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

wang-zidu/3ddfa-v3 officialmentioned in papermentioned on GitHubpytorchMIT report
wang-zidu/s2td-face mentioned on GitHubpytorch 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

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

3D Face ReconstructionFace ReconstructionSegmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction REALY 3DDFA-v3 @cheek 1.110 (±0.328) #4 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v3 @forehead 1.809 (±0.394) #4 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v3 @mouth 1.237 (±0.375) #4 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v3 @nose 1.584 (±0.308) #4 of 24 Archive leaderboard report
3D Face Reconstruction REALY 3DDFA-v3 all 1.435 #4 of 24 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v3 @cheek 1.073 (±0.316) #3 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v3 @forehead 1.861 (±0.421) #3 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v3 @mouth 1.209 (±0.369) #3 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v3 @nose 1.621 (±0.312) #3 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) 3DDFA-v3 all 1.441 #3 of 19 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