Related papers: Scalable and Generalizable Correspondence Pruning …

Correspondence pruning aims to establish reliable correspondences between two related images and recover relative camera motion. Existing approaches often employ a progressive strategy to handle the local and global contexts, with a…

Recent learning-based approaches, in which models are trained by single-view images have shown promising results for monocular 3D face reconstruction, but they suffer from the ill-posed face pose and depth ambiguity issue. In contrast to…

We develop a deep architecture to learn to find good correspondences for wide-baseline stereo. Given a set of putative sparse matches and the camera intrinsics, we train our network in an end-to-end fashion to label the correspondences as…

Most state-of-the-art deep geometric learning single-view reconstruction approaches rely on encoder-decoder architectures that output either shape parametrizations or implicit representations. However, these representations rarely preserve…

In this paper, we aim to recover the 3D human pose from 2D body joints of a single image. The major challenge in this task is the depth ambiguity since different 3D poses may produce similar 2D poses. Although many recent advances in this…

Two-view correspondence pruning aims to accurately remove incorrect correspondences (outliers) from initial ones and is widely applied to various computer vision tasks. Current popular strategies adopt multilayer perceptron (MLP) as the…

Compressing neural networks without retraining is vital for deployment at scale. We study calibration-free compression through the lens of projection geometry: structured pruning is an axis-aligned projection, whereas model folding performs…

Pruning is widely used to reduce the complexity of deep learning models, but its effects on interpretability and representation learning remain poorly understood. This paper investigates how pruning influences vision models across three key…

In this work, we focus on the task of learning and representing dense correspondences in deformable object categories. While this problem has been considered before, solutions so far have been rather ad-hoc for specific object types (i.e.,…

We present a method for finding correspondence between 3D models. From an initial set of feature correspondences, our method uses a fast voting scheme to separate the inliers from the outliers. The novelty of our method lies in the use of a…

Seeking consistent point-to-point correspondences between 3D rigid data (point clouds, meshes, or depth maps) is a fundamental problem in 3D computer vision. While a number of correspondence selection methods have been proposed in recent…

3D scene reconstruction is fundamental for spatial intelligence applications such as AR, robotics, and digital twins. Traditional multi-view stereo struggles with sparse viewpoints or low-texture regions, while neural rendering approaches,…

In this paper we explore using self-supervised correspondence for improving the generalization performance and sample efficiency of visuomotor policy learning. Prior work has primarily used approaches such as autoencoding, pose-based…

Learning dense correspondences across deformable 3D shapes remains a long-standing challenge due to structural variability, non-isometric deformation, and inconsistent topology. Existing methods typically trade off generalization, geometric…

This paper proposes a GeneraLIst encoder-Decoder (GLID) pre-training method for better handling various downstream computer vision tasks. While self-supervised pre-training approaches, e.g., Masked Autoencoder, have shown success in…

Two-hand reconstruction from monocular images is hampered by complex poses and severe occlusions, which often cause interaction misalignment and two-hand penetration. We address this by decoupling the problem into 2D structural alignment…

The key challenge in learning dense correspondences lies in the lack of ground-truth matches for real image pairs. While photometric consistency losses provide unsupervised alternatives, they struggle with large appearance changes, which…

Pruning is a well-known mechanism for reducing the computational cost of deep convolutional networks. However, studies have shown the potential of pruning as a form of regularization, which reduces overfitting and improves generalization.…

Standard training metrics like loss fail to explain the emergence of complex capabilities in large language models. We take a spectral approach to investigate the geometry of learned representations across pretraining and post-training,…

Category-level 6D object pose and size estimation is to predict full pose configurations of rotation, translation, and size for object instances observed in single, arbitrary views of cluttered scenes. In this paper, we propose a new method…