Recent advances in large-scale pretraining have yielded visual foundation models with
strong capabilities. Not only can recent models generalize to arbitrary images for their …

Abstract We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale
benchmark designed to advance the development and evaluation of pose estimation …

We present SHINOBI an end-to-end framework for the reconstruction of shape material and
illumination from object images captured with varying lighting pose and background. Inverse …

Inferring the 3D structure underlying a set of multi-view images typically requires solving two
co-dependent tasks--accurate 3D reconstruction requires precise camera poses, and …

Model customization introduces new concepts to existing text-to-image models, enabling the
generation of the new concept in novel contexts. However, such methods lack accurate …

Recent works in inverse rendering have shown promise in using multi-view images of an
object to recover shape, albedo, and materials. However, the recovered components often …

Contrastive Language-Image Pre-training (CLIP) models have shown significant potential,
particularly in zero-shot classification across diverse distribution shifts. Building on existing …

Agglomerative models have recently emerged as a powerful approach to training vision
foundation models, leveraging multi-teacher distillation from existing models such as CLIP …

We propose 3D Congealing, a novel problem of 3D-aware alignment for 2D images
capturing semantically similar objects. Given a collection of unlabeled Internet images, our …

We introduce PACE (Pose Annotations in Cluttered Environments), a large-scale benchmark
designed to advance the development and evaluation of pose estimation methods in …