Recovering physically-based material properties (albedo, roughness, metallic) from a single photograph is a classic ill-posed problem: any dark pixel could be a dark surface or a poorly-lit one. Prior diffusion-based approaches try to regress these material maps directly, but since real ground-truth PBR data doesn’t exist, those models are trained only on synthetic interiors — …
We estimate 3D geometry from sparse grasp measurements by training a flow matching model inside the 32-dimensional latent space of an occupancy VAE. Contact points, fingertip poses, or joint angles alone are each sufficient to decode plausible shapes. Explicit geometric representations such as voxel grids and meshes scale poorly with resolution, which makes them expensive …
Novel View Synthesis (NVS) aims to generate images of a scene from viewpoints that were not originally captured. Given a set of reference images and their camera poses, the goal is to synthesize a realistic image from a new camera position. This is an important problem in computer vision with applications in 3D reconstruction, robotics, …
When cooking I’m using recipes from different pages. Some have a great formatting and display ingredients next to the individual steps, other’s torture me with informing me about the author’s familiy history before showing the actual recipe. I’ve always wanted to use GenAI to create a recipe app that ingests recipes and formats them exactly …