← Search

Yajing Bai

2 accepted papers

2026

Learning Latent Proxies for Controllable Single-Image Relighting

CVPR 2026

Single-image relighting is highly under-constrained: small illumination changes can produce large, nonlinear variations in shading, shadows, and specularities, while geometry and materials remain unobserved. Existing diffusion-based approaches either rely on intrinsic- or G-buffer-based pipelines th

Cited by 0SourceScholar
2024

FSC: Few-point Shape Completion

CVPR 2024poster

While previous studies have demonstrated successful 3D object shape completion with a sufficient number of points they often fail in scenarios when a few points e.g. tens of points are observed. Surprisingly via entropy analysis we find that even a few points e.g. 64 points could retain substantial…