首页/论文/1412.0477

arXiv 1412.04772016-08-16cs.CV

Recovering Spatiotemporal Correspondence between Deformable Objects by Exploiting Consistent Foreground Motion in Video

University of Edinburgh（爱丁堡大学）；Google Research（谷歌研究院）

Luca Del Pero, Susanna Ricco, Rahul Sukthankar, Vittorio Ferrari

备注：: 9 pages, 14 figures. This article is obsolete. Its contents are now covered in arXiv:1511.09319, where we discuss a comprehensive system for behavior discovery and spatial alignment of articulated object classes from unstructured video (available at https://arxiv.org/abs/1511.09319)

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

英文摘要相关论文

英文摘要：

Given unstructured videos of deformable objects, we automatically recover spatiotemporal correspondences to map one object to another (such as animals in the wild). While traditional methods based on appearance fail in such challenging conditions, we exploit consistency in object motion between instances. Our approach discovers pairs of short video intervals where the object moves in a consistent manner and uses these candidates as seeds for spatial alignment. We model the spatial correspondence between the point trajectories on the object in one interval to those in the other using a time-varying Thin Plate Spline deformation model. On a large dataset of tiger and horse videos, our method automatically aligns thousands of pairs of frames to a high accuracy, and outperforms the popular SIFT Flow algorithm.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

阅读原文

阅读 PDF ↗

arXiv 页面 ↗HTML 原文 ↗

本文内容

英文摘要相关论文

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

继续探索

相关论文

Cascade Image Matting with Deformable Graph Refinement

Tsinghua University（清华大学）；Kuaishou Technology（快手科技）

Image matting refers to the estimation of the opacity of foreground objects. It requires correct contours and fine details of foreground objects for the matting results. To better accomplish human image matting tasks, we propose the Cascade Image Matting Network with Deformable Graph Refinement, which can automatically predict precise alpha mattes from single human images without any additional inputs. We adopt a network cascade architecture to perform matting from low-to-high resolution, which corresponds to coarse-to-fine optimization. We also introduce the Deformable Graph Refinement (DGR) …

2021-05-08cs.CV

Densely Deformable Efficient Salient Object Detection Network

Sejong University（世宗大学）；The Australian National University（澳大利亚国立大学）；Data61-CSIRO（Data61-联邦科学与工业研究组织）；University of Technology Sydney（悉尼科技大学）

Salient Object Detection (SOD) domain using RGB-D data has lately emerged with some current models' adequately precise results. However, they have restrained generalization abilities and intensive computational complexity. In this paper, inspired by the best background/foreground separation abilities of deformable convolutions, we employ them in our Densely Deformable Network (DDNet) to achieve efficient SOD. The salient regions from densely deformable convolutions are further refined using transposed convolutions to optimally generate the saliency maps. Quantitative and qualitative evaluation…

2021-02-12cs.CV

从视频中恢复动态3D草图

Recovering Dynamic 3D Sketches from Videos

Seoul National University（首尔大学）

针对视频中3D运动理解难题，提出Liv3Stroke方法，利用可变形3D曲线抽象运动特征，实现鲁棒且显式的3D运动分析。

2025-03-27cs.CV

Multiple-Kernel Based Vehicle Tracking Using 3D Deformable Model and Camera Self-Calibration

University of Washington（华盛顿大学）；University of Tokyo（东京大学）；Microsoft Research（微软研究院）

Tracking of multiple objects is an important application in AI City geared towards solving salient problems related to safety and congestion in an urban environment. Frequent occlusion in traffic surveillance has been a major problem in this research field. In this challenge, we propose a model-based vehicle localization method, which builds a kernel at each patch of the 3D deformable vehicle model and associates them with constraints in 3D space. The proposed method utilizes shape fitness evaluation besides color information to track vehicle objects robustly and efficiently. To build 3D car m…

2017-08-22cs.CV

Deformable Kernels: Adapting Effective Receptive Fields for Object Deformation

UC Berkeley（加州大学伯克利分校）；Microsoft Research Asia（微软亚洲研究院）；University of Science and Technology of China（中国科学技术大学）

Convolutional networks are not aware of an object's geometric variations, which leads to inefficient utilization of model and data capacity. To overcome this issue, recent works on deformation modeling seek to spatially reconfigure the data towards a common arrangement such that semantic recognition suffers less from deformation. This is typically done by augmenting static operators with learned free-form sampling grids in the image space, dynamically tuned to the data and task for adapting the receptive field. Yet adapting the receptive field does not quite reach the actual goal -- what reall…

2020-02-12cs.CV

FiG-NeRF: Figure-Ground Neural Radiance Fields for 3D Object Category Modelling

Google Research（谷歌研究院）；University of Washington（华盛顿大学）

We investigate the use of Neural Radiance Fields (NeRF) to learn high quality 3D object category models from collections of input images. In contrast to previous work, we are able to do this whilst simultaneously separating foreground objects from their varying backgrounds. We achieve this via a 2-component NeRF model, FiG-NeRF, that prefers explanation of the scene as a geometrically constant background and a deformable foreground that represents the object category. We show that this method can learn accurate 3D object category models using only photometric supervision and casually captured …

2021-04-17cs.CV

更多相关论文收起更多论文

Learning Category-Specific Mesh Reconstruction from Image Collections

University of California, Berkeley（加州大学伯克利分校）

We present a learning framework for recovering the 3D shape, camera, and texture of an object from a single image. The shape is represented as a deformable 3D mesh model of an object category where a shape is parameterized by a learned mean shape and per-instance predicted deformation. Our approach allows leveraging an annotated image collection for training, where the deformable model and the 3D prediction mechanism are learned without relying on ground-truth 3D or multi-view supervision. Our representation enables us to go beyond existing 3D prediction approaches by incorporating texture inf…

2018-07-30cs.CV

虚拟宠物：3D场景中的可动画动物生成

Virtual Pets: Animatable Animal Generation in 3D Scenes

UIUC（伊利诺伊大学厄巴纳-香槟分校）；Snap Research（Snap研究院）；UC Merced（加州大学默塞德分校）；University of Toronto（多伦多大学）

针对3D场景中动物运动数据稀缺的问题，提出Virtual Pet流水线，利用单目视频重建NeRF并训练条件3D运动模型，生成真实多样的4D动物动画，在猫视频上验证有效性。

2023-12-21cs.CV

DenseReg: Fully Convolutional Dense Shape Regression In-the-Wild

Inria（法国国家信息与自动化研究所）

In this work we use deep learning to establish dense correspondences between a 3D object model and an image "in the wild". We introduce "DenseReg", a fully-convolutional neural network (F-CNN) that densely regresses at every foreground pixel a pair of U-V template coordinates in a single feedforward pass. To train DenseReg we construct a supervision signal by combining 3D deformable model fitting and 2D landmark annotations. We define the regression task in terms of the intrinsic, U-V coordinates of a 3D deformable model that is brought into correspondence with image instances at training time…

2018-03-11cs.CV

Recovering 6D Object Pose and Predicting Next-Best-View in the Crowd

Imperial College London（帝国理工学院）；Center for Research & Technology Hellas (CERTH)（希腊研究与技术中心（CERTH））

Object detection and 6D pose estimation in the crowd (scenes with multiple object instances, severe foreground occlusions and background distractors), has become an important problem in many rapidly evolving technological areas such as robotics and augmented reality. Single shot-based 6D pose estimators with manually designed features are still unable to tackle the above challenges, motivating the research towards unsupervised feature learning and next-best-view estimation. In this work, we present a complete framework for both single shot-based 6D object pose estimation and next-best-view pre…

2016-04-19cs.CV

Approximated Robust Principal Component Analysis for Improved General Scene Background Subtraction

The research reported in this paper addresses the fundamental task of separation of locally moving or deforming image areas from a static or globally moving background. It builds on the latest developments in the field of robust principal component analysis, specifically, the recently reported practical solutions for the long-standing problem of recovering the low-rank and sparse parts of a large matrix made up of the sum of these two components. This article addresses a few critical issues including: embedding global motion parameters in the matrix decomposition model, i.e., estimation of glo…

2016-03-18cs.CVstat.AP

PBDyG: 用于运动感知穿衣人体化身的基于位置的动态高斯

PBDyG: Position Based Dynamic Gaussians for Motion-Aware Clothed Human Avatars

Kyoto University（京都大学）；University of California, Berkeley（加州大学伯克利分校）

该研究提出PBDyG穿衣人体建模方法，结合蒙皮SMPL身体与3D高斯布料模型，通过物理模拟实现运动相关的布料形变，可从多视角RGB视频估计物理属性，有效提升高形变服装化身的重建效果。

2024-12-06cs.CV

FreeOrbit4D: 通过前景完整4D重建实现免训练的任意相机重定向

FreeOrbit4D: Training-Free Arbitrary Camera Redirection for Monocular Videos via Foreground-Complete 4D Reconstruction

University of Illinois Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Pennsylvania（宾夕法尼亚大学）；Eyeline Labs（Eyeline实验室）

本文提出FreeOrbit4D，一种无需训练的框架，通过恢复完整的前景4D代理来解决大角度重定向中的几何模糊问题，从而生成更真实且时间一致的视频。

2026-05-19cs.AIcs.CVcs.GR

通过一步扩散模型平滑现实世界的时空视频超分辨率

Taming Real-World Space-Time Video Super-Resolution with One-Step Diffusion

Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学学院）；Visual Intelligence + X International Cooperation Joint Laboratory of MOE, Beijing（教育部视觉智能+X国际合作联合实验室）；Innovation School of Artificial Intelligence, Hefei University of Technology（合肥工业大学人工智能创新学院）；School of Control Science and Engineering, Shandong University（山东大学控制科学与工程学院）

本文提出OSDEnhancer框架，通过一步扩散模型实现鲁棒的时空视频超分辨率，解决了现实世界中复杂未知退化的问题，通过线性初始化和分治策略提升时空动态和纹理恢复性能。

2026-05-19cs.CVcs.GR