Generative models can produce impressively realistic images. This paper demonstrates that
generated images have geometric features different from those of real images. We build a …

This paper studies amodal image segmentation: predicting entire object segmentation
masks including both visible and invisible (occluded) parts. In previous work the amodal …

Generative models excel at mimicking real scenes, suggesting they might inherently encode
important intrinsic scene properties. In this paper, we aim to explore the following key …

We introduce LightIt a method for explicit illumination control for image generation. Recent
generative methods lack lighting control which is crucial to numerous artistic aspects of …

One of the key components within diffusion models is the UNet for noise prediction. While
several works have explored basic properties of the UNet decoder, its encoder largely …

Estimating the pose of objects from images is a crucial task of 3D scene understanding and
recent approaches have shown promising results on very large benchmarks. However these …

Our brain can effortlessly recognize objects even when partially hidden from view. Seeing
the visible of the hidden is called amodal completion; however this task remains a challenge …

Complex 3D scene understanding has gained increasing attention, with scene encoding
strategies playing a crucial role in this success. However, the optimal scene encoding …

Large-scale vision foundation models have demonstrated remarkable success across
various tasks, underscoring their robust generalization capabilities. While their proficiency in …

Text-to-image diffusion models generate impressive and realistic images, but do they learn
to represent the 3D world from only 2D supervision? We demonstrate that yes, certain 3D …