Papers › Towards Realistic Generative 3D Face Models

Towards Realistic Generative 3D Face Models

24 Apr 2023arXiv:2304.12483archive 2025-07-28

Aashish Rai, Hiresh Gupta, Ayush Pandey, Francisco Vicente Carrasco, Shingo Jason Takagi, Amaury Aubel, Daeil Kim, Aayush Prakash, Fernando de la Torre

In recent years, there has been significant progress in 2D generative face models fueled by applications such as animation, synthetic data generation, and digital avatars. However, due to the absence of 3D information, these 2D models often struggle to accurately disentangle facial attributes like pose, expression, and illumination, limiting their editing capabilities. To address this limitation, this paper proposes a 3D controllable generative face model to produce high-quality albedo and precise 3D shape leveraging existing 2D generative models. By combining 2D face generative models with semantic face manipulation, this method enables editing of detailed 3D rendered faces. The proposed framework utilizes an alternating descent optimization approach over shape and albedo. Differentiable rendering is used to train high-quality shapes and albedo without 3D supervision. Moreover, this approach outperforms the state-of-the-art (SOTA) methods in the well-known NoW benchmark for shape reconstruction. It also outperforms the SOTA reconstruction models in recovering rendered faces' identities across novel poses by an average of 10%. Additionally, the paper demonstrates direct control of expressions in 3D faces by exploiting latent space leading to text-based editing of 3D faces.

PaperPDFCode

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

Code

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 ModelSynthetic Data Generation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
3D Face Reconstruction REALY AlbedoGAN @cheek 1.141 (±0.303) #8 of 24 Archive leaderboard report
3D Face Reconstruction REALY AlbedoGAN @forehead 2.102 (±0.512) #8 of 24 Archive leaderboard report
3D Face Reconstruction REALY AlbedoGAN @mouth 2.087 (±0.839) #8 of 24 Archive leaderboard report
3D Face Reconstruction REALY AlbedoGAN @nose 1.656 (±0.374) #8 of 24 Archive leaderboard report
3D Face Reconstruction REALY AlbedoGAN all 1.746 #8 of 24 Archive leaderboard report
3D Face Reconstruction REALY (side-view) AlbedoGAN @cheek 1.112 (±0.278) #6 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) AlbedoGAN @forehead 2.142 (±0.554) #6 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) AlbedoGAN @mouth 2.218 (±0.952) #6 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) AlbedoGAN @nose 1.576 (±0.338) #6 of 19 Archive leaderboard report
3D Face Reconstruction REALY (side-view) AlbedoGAN all 1.762 #6 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