4 papers
AdaLoop: Thinking with the Vision Encoder
Xinran Nicole Han, Yiyang Lu, Katelyn Gan +1
Most vision-language models (VLMs) treat the vision encoder as a static feature extractor: it encodes an image once, independently of the question, and leaves subsequent reasoning…
Under One Sun: Multi-Object Generative Perception of Materials and Illumination
Nobuo Yoshii, Xinran Nicole Han, Ryo Kawahara +2
We introduce Multi-Object Generative Perception (MultiGP), a generative inverse rendering method for stochastic sampling of all radiometric constituents -- reflectance, texture, an…
CObL: Toward Zero-Shot Ordinal Layering without User Prompting
Aneel Damaraju, Dean Hazineh, Todd Zickler
Vision benefits from grouping pixels into objects and understanding their spatial relationships, both laterally and in depth. We capture this with a scene representation comprising…
Filterless Snapshot Hyperspectral Imaging using Guided Patch Diffusion
Dean Hazineh, Luca Sacchi, Davide Cassara +2
We consider the problem of reconstructing a HxWx31 hyperspectral image from a grayscale snapshot measurement that is captured using only a single diffractive lens and a…