Infinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detection

Simple item page
dc.contributor.authorChandran, P.en_US
dc.contributor.authorZoss, G.en_US
dc.contributor.authorGotardo, P.en_US
dc.contributor.authorBradley, D.en_US
dc.contributor.editorAlliez, Pierreen_US
dc.contributor.editorWimmer, Michaelen_US
dc.date.accessioned2024-12-19T11:15:43Z
dc.date.available2024-12-19T11:15:43Z
dc.date.issued2024
dc.description.abstractIn this paper, we examine three important issues in the practical use of state‐of‐the‐art facial landmark detectors and show how a combination of specific architectural modifications can directly improve their accuracy and temporal stability. First, many facial landmark detectors require a face normalization step as a pre‐process, often accomplished by a separately trained neural network that crops and resizes the face in the input image. There is no guarantee that this pre‐trained network performs optimal face normalization for the task of landmark detection. Thus, we instead analyse the use of a spatial transformer network that is trained alongside the landmark detector in an unsupervised manner, jointly learning an optimal face normalization and landmark detection by a single neural network. Second, we show that modifying the output head of the landmark predictor to infer landmarks in a canonical 3D space rather than directly in 2D can further improve accuracy. To convert the predicted 3D landmarks into screen‐space, we additionally predict the camera intrinsics and head pose from the input image. As a side benefit, this allows to predict the 3D face shape from a given image only using 2D landmarks as supervision, which is useful in determining landmark visibility among other things. Third, when training a landmark detector on multiple datasets at the same time, annotation inconsistencies across datasets forces the network to produce a sub‐optimal average. We propose to add a semantic correction network to address this issue. This additional lightweight neural network is trained alongside the landmark detector, without requiring any additional supervision. While the insights of this paper can be applied to most common landmark detectors, we specifically target a recently proposed continuous 2D landmark detector to demonstrate how each of our additions leads to meaningful improvements over the state‐of‐the‐art on standard benchmarks.en_US
dc.description.number6
dc.description.sectionheadersMajor Revision from Eurographics Conference
dc.description.seriesinformationComputer Graphics Forum
dc.description.volume43
dc.identifier.doi10.1111/cgf.15126
dc.identifier.pages13 pages
dc.identifier.urihttps://doi.org/10.1111/cgf.15126
dc.identifier.urihttps://diglib.eg.org/handle/10.1111/cgf15126
dc.publisher© 2024 Eurographics ‐ The European Association for Computer Graphics and John Wiley & Sons Ltd.en_US
dc.subjectanimation
dc.subjectfacial animation
dc.subjectimage and video processing
dc.titleInfinite 3D Landmarks: Improving Continuous 2D Facial Landmark Detectionen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
17_cgf15126.pdf
Size:
18.09 MB
Format:
Adobe Portable Document Format
Download
Collections
43-Issue 6