Related papers: MV-RoMa: From Pairwise Matching into Multi-View Tr…
While current multi-frame restoration methods combine information from multiple input images using 2D alignment techniques, recent advances in novel view synthesis are paving the way for a new paradigm relying on volumetric scene…
Reliable omnidirectional depth estimation from multi-fisheye stereo matching is pivotal to many applications, such as embodied robotics. Existing approaches either rely on spherical sweeping with heuristic fusion strategies to build the…
Feature representation plays a crucial role in visual correspondence, and recent methods for image matching resort to deeply stacked convolutional layers. These models, however, are both monolithic and static in the sense that they…
Self-supervised video correspondence learning depends on the ability to accurately associate pixels between video frames that correspond to the same visual object. However, achieving reliable pixel matching without supervision remains a…
Dense semantic forecasting anticipates future events in video by inferring pixel-level semantics of an unobserved future image. We present a novel approach that is applicable to various single-frame architectures and tasks. Our approach…
Achieving high-fidelity 3D surface reconstruction while preserving fine details remains challenging, especially in the presence of materials with complex reflectance properties and without a dense-view setup. In this paper, we introduce a…
We propose a deep learning approach for finding dense correspondences between 3D scans of people. Our method requires only partial geometric information in the form of two depth maps or partial reconstructed surfaces, works for humans in…
Multi-view Stereo (MVS) aims to estimate depth and reconstruct 3D point clouds from a series of overlapping images. Recent learning-based MVS frameworks overlook the geometric information embedded in features and correlations, leading to…
This paper presents a new end-to-end semi-supervised framework to learn a dense keypoint detector using unlabeled multiview images. A key challenge lies in finding the exact correspondences between the dense keypoints in multiple views…
A fundamental problem in robotic perception is matching identical objects or data, with applications such as loop closure detection, place recognition, object tracking, and map fusion. While the problem becomes considerably more challenging…
We propose an approach to reconstruct dense three-dimensional (3D) model of tissue surface from stereo optical videos in real-time, the basic idea of which is to first extract 3D information from video frames by using stereo matching, and…
Context has proven to be one of the most important factors in object layout reasoning for 3D scene understanding. Existing deep contextual models either learn holistic features for context encoding or rely on pre-defined scene templates for…
Estimating 3D mesh of the human body from a single 2D image is an important task with many applications such as augmented reality and Human-Robot interaction. However, prior works reconstructed 3D mesh from global image feature extracted by…
Multi-object tracking from RGB-D video sequences is a challenging problem due to the combination of changing viewpoints, motion, and occlusions over time. We observe that having the complete geometry of objects aids in their tracking, and…
Video restoration (VR) aims to recover high-quality videos from degraded ones. Although recent zero-shot VR methods using pre-trained diffusion models (DMs) show good promise, they suffer from approximation errors during reverse diffusion…
Conventional techniques to establish dense correspondences across visually or semantically similar images focused on designing a task-specific matching prior, which is difficult to model. To overcome this, recent learning-based methods have…
Leveraging multi-view diffusion models as priors for 3D optimization have alleviated the problem of 3D consistency, e.g., the Janus face problem or the content drift problem, in zero-shot text-to-3D models. However, the 3D geometric…
In text-to-image person retrieval tasks, the diversity of natural language expressions and the implicitness of visual semantics often lead to the problem of Expression Drift, where semantically equivalent texts exhibit significant feature…
Learning-based multi-view stereo (MVS) has gained fine reconstructions on popular datasets. However, supervised learning methods require ground truth for training, which is hard to be collected, especially for the large-scale datasets.…
We introduce the first data-driven multi-view 3D point tracker, designed to track arbitrary points in dynamic scenes using multiple camera views. Unlike existing monocular trackers, which struggle with depth ambiguities and occlusion, or…