SOTAVerified

3D Face Reconstruction

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 )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–10 of 211 papers

TitleStatusHype
3D Face Reconstruction Error Decomposed: A Modular Benchmark for Fair and Fast Method EvaluationCode0
Pixel3DMM: Versatile Screen-Space Priors for Single-Image 3D Face Reconstruction—0
Sketch-1-to-3: One Single Sketch to 3D Detailed Face Reconstruction—0
Learning Person-Specific Animatable Face Models from In-the-Wild Images via a Shared Base ModelCode0
S^3-Face: SSS-Compliant Facial Reflectance Estimation via Diffusion Priors—0
3D Face Reconstruction With Geometry Details From a Single Color Image Under Occluded Scenes—0
Generative Landmarks Guided Eyeglasses Removal 3D Face Reconstruction—0
Generative Face Parsing Map Guided 3D Face Reconstruction Under Occluded Scenes—0
3D Face Reconstruction From Radar Images—0
OFER: Occluded Face Expression Reconstruction—0
Show:102550
← PrevPage 1 of 22Next →
All datasetsREALYREALY (side-view)NoW BenchmarkFlorenceAFLW2000-3DStirling-HQ (FG2018 3D face reconstruction challenge)Stirling-LQ (FG2018 3D face reconstruction challenge)13.8

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DeFAMean NME 5.65—Unverified
23DDFAMean NME 5.37—Unverified
3PRNMean NME 3.96—Unverified
43DDFA-V2Mean NME 3.56—Unverified
5B-spline FFDMean NME 3.51—Unverified
6VGG-FMean NME 3.42—Unverified
7SADRNetMean NME 3.25—Unverified
8DSFNet-isMean NME3.16—Unverified