As an emerging and challenging problem in the computer vision community, weakly
supervised object localization and detection plays an important role for developing new …

Augmented reality (AR) has proven to be an invaluable interactive medium to reduce
cognitive load by bridging the gap between the task-at-hand and relevant information by …

Abstract We introduce Zero-1-to-3, a framework for changing the camera viewpoint of an
object given just a single RGB image. To perform novel view synthesis in this …

Single image 3D reconstruction is an important but challenging task that requires extensive
knowledge of our natural world. Many existing methods solve this problem by optimizing a …

We present DreamBooth3D, an approach to personalize text-to-3D generative models from
as few as 3-6 casually captured images of a subject. Our approach combines recent …

Recent advancements in open-world 3D object generation have been remarkable with
image-to-3D methods offering superior fine-grained control over their text-to-3D …

Novel view synthesis from a single image requires inferring occluded regions of objects and
scenes whilst simultaneously maintaining semantic and physical consistency with the input …

Humans can easily imagine the complete 3D geometry of occluded objects and scenes. This
appealing ability is vital for recognition and understanding. To enable such capability in AI …

As a promising scheme of self-supervised learning, masked autoencoding has significantly
advanced natural language processing and computer vision. Inspired by this, we propose a …

Masked Autoencoders (MAE) have shown great potentials in self-supervised pre-training for
language and 2D image transformers. However, it still remains an open question on how to …