Publications
You can also find my articles on my Google Scholar profile .
SEM-ROVER: Semantic Voxel-Guided Diffusion for Large-Scale Driving Scene Generation
ECCV 2026A framework for generating large-scale, multiview-consistent outdoor driving scenes using a semantic-conditioned 3D diffusion model, Σ-Voxfield representation, progressive spatial outpainting, and deferred rendering.
SWAG: Splatting in the Wild Images with Appearance-conditioned Gaussians
ECCV 2024A method extending 3D Gaussian Splatting to unconstrained, in-the-wild image collections by modelling appearance changes and transient scene content.