4 papers
MeshQuery: Agentic Seam Planning for UV Parametrization
Marco Schouten, Arthur Roullier, Elie Michel +3
We present MeshQuery, a training-free agentic approach to automatic UV unwrapping of production-grade quad meshes. A Vision-Language Model (VLM) plans artist-aligned seams using a…
HiddenObjects: Scalable Spatial Prior Extraction for Object Placement from Diffusion Models
Marco Schouten, Ioannis Siglidis, Serge Belongie +1
We learn explicit, class-conditioned spatial priors for object placement in natural scenes by distilling placement knowledge from text-conditioned diffusion models. Prior methods r…
Sherlock Your Queries: Learning to Ask the Right Questions for Dialogue-Based Retrieval
Dong Yun, Marco Schouten, Dim Papadopoulos
User queries in information retrieval are often ambiguous, making it challenging for systems to identify a user's target from a single query. While recent dialogue-based interactiv…
POEM: Precise Object-level Editing via MLLM control
Marco Schouten, Mehmet Onurcan Kaya, Serge Belongie +1
Diffusion models have significantly improved text-to-image generation, producing high-quality, realistic images from textual descriptions. Beyond generation, object-level image edi…