DiTGaze: Geometry-Conditioned Diffusion Augmentation for Few-Shot Gaze Estimation
Abstract
Accurate person-specific gaze estimation benefits from labeled user data, but collecting images that densely cover gaze directions is burdensome. We present DiTGaze, a calibration-efficient augmentation system that follows a two-stream 3D Gaussian Splatting backbone and reformulates its convolutional rendering stage as a geometry-conditioned latent Diffusion Transformer (DiT). A learnable projection and frozen VAE bridge rasterized Gaussian features to latent tokens, while timestep and identity/expression conditioning are integrated through Adaptive Layer Normalization. Intermediate yaw-pitch sampling densifies gaze supervision, and an orthogonality constraint reduces interference between gaze, pose, and expression. On ETH-XGaze, DiTGaze reduces generator-level gaze error by 4.1 percent relative to GazeGaussian. In our runs of the expanded downstream protocol, it ranks first at every calibration budget from one to nine real images; the repeated primary comparison at N = 9 reduces subject-level estimator error by 0.73 degrees and improves 14 of 15 identities (p < 0.001). These results connect the proposed generator changes to statistically supported few-shot personalization gains.
