Global Non-rigid Alignment of Surface Sequences

Budd, Chris; Huang, Peng; Klaudiny, Martin; Hilton, Adrian

doi:10.1007/s11263-012-0553-4

Cited by 66 publications

(82 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[20] in camera/object tracking, and by non-sequential surface registration methods [4,14]. In these works the tracking task is eased by reducing the discrepancy between the model and the input data to be matched.…”

Section: Introductionmentioning

confidence: 99%

Human Shape and Pose Tracking Using Keyframes

Huang

Boyer

Navab

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

This paper considers human tracking in multi-view setups and investigates a robust strategy that learns online key poses to drive a shape tracking method. The interest arises in realistic dynamic scenes where occlusions or segmentation errors occur. The corrupted observations present missing data and outliers that deteriorate tracking results. We propose to use key poses of the tracked person as multiple reference models. In contrast to many existing approaches that rely on a single reference model, multiple templates represent a larger variability of human poses. They provide therefore better initial hypotheses when tracking with noisy data. Our approach identifies these reference models online as distinctive keyframes during tracking. The most suitable one is then chosen as the reference at each frame. In addition, taking advantage of the proximity between successive frames, an efficient outlier handling technique is proposed to prevent from associating the model to irrelevant outliers. The two strategies are successfully experimented with a surface deformation framework that recovers both the pose and the shape. Evaluations on existing datasets also demonstrate their benefits with respect to the state of the art.

show abstract

Section: Introductionmentioning

confidence: 99%

Human Shape and Pose Tracking Using Keyframes

Huang

Boyer

Navab

et al. 2014

2014 IEEE Conference on Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

show abstract

“…Our approach is motivated by previous non-sequential approaches to surface alignment [29,24,30] which have been shown to achieve robust 4D alignment of complete surface reconstructions over multiple sequences with large non-rigid deformations. These approaches use an intermediate tree structure to represent the unaligned data based on a measure of shape similarity.…”

Section: Methodsmentioning

confidence: 99%

“…A number of approaches for surface reconstruction [19,20] do not produce temporally coherent models for an entire sequence rather they align pairs of frames sequentially. Other methods proposed for 4D alignment of surface reconstructions assume that a complete mesh of the dynamic object is available for the entire sequence [21,22,23,24,25]. Partial surface tracking methods for single view [26] and RGBD data [8,27] perform sequential alignment of the reconstructions using frame-to-frame tracking.…”

Section: Related Workmentioning

confidence: 99%

“…Sequential methods suffer from drift due to accumulation of errors in alignment between successive frames and failure is observed due to large non-rigid motion. Non-sequential approaches address these issues but existing methods require complete surface reconstruction [24,25]. In this paper we propose a nonsequential method to align partial surface reconstructions of dynamic objects for general dynamic outdoor and indoor scenes with large non-rigid motions across sequences and views.…”

Section: Related Workmentioning

confidence: 99%

“…Previous research has employed a tree structure to represent nonrigid shape of complete surfaces to achieve robust non-sequential alignment for sequences with large non-rigid deformations [29,24,30]. Inspired by the success of these approaches we propose the 4D Match Tree as an intermediate representation for alignment of partial non-rigid surface reconstructions.…”

Section: D Match Trees For Non-sequential Alignmentmentioning

confidence: 99%

See 2 more Smart Citations

4D Match Trees for Non-rigid Surface Alignment

Mustafa

Kim

Hilton

2016

Computer Vision – ECCV 2016

Self Cite

View full text Add to dashboard Cite

Abstract. This paper presents a method for dense 4D temporal alignment of partial reconstructions of non-rigid surfaces observed from single or multiple moving cameras of complex scenes. 4D Match Trees are introduced for robust global alignment of non-rigid shape based on the similarity between images across sequences and views. Wide-timeframe sparse correspondence between arbitrary pairs of images is established using a segmentation-based feature detector (SFD) which is demonstrated to give improved matching of non-rigid shape. Sparse SFD correspondence allows the similarity between any pair of image frames to be estimated for moving cameras and multiple views. This enables the 4D Match Tree to be constructed which minimises the observed change in non-rigid shape for global alignment across all images. Dense 4D temporal correspondence across all frames is then estimated by traversing the 4D Match tree using optical flow initialised from the sparse feature matches. The approach is evaluated on single and multiple view images sequences for alignment of partial surface reconstructions of dynamic objects in complex indoor and outdoor scenes to obtain a temporally consistent 4D representation. Comparison to previous 2D and 3D scene flow demonstrates that 4D Match Trees achieve reduced errors due to drift and improved robustness to large non-rigid deformations.

show abstract

Volumetric Performance Capture from Minimal Camera Viewpoints

Gilbert

Volino

Collomosse

et al. 2018

Computer Vision – ECCV 2018

Self Cite

View full text Add to dashboard Cite

We present a convolutional autoencoder that enables high fidelity volumetric reconstructions of human performance to be captured from multi-view video comprising only a small set of camera views. Our method yields similar end-to-end reconstruction error to that of a probabilistic visual hull computed using significantly more (double or more) viewpoints. We use a deep prior implicitly learned by the autoencoder trained over a dataset of view-ablated multi-view video footage of a wide range of subjects and actions. This opens up the possibility of high-end volumetric performance capture in on-set and prosumer scenarios where time or cost prohibit a high witness camera count. Fig. 1. Two high fidelity character models (JP, Magician) where 3D geometry was fully reconstructed using only two wide-baseline camera views via our proposed method.

show abstract

Global Non-rigid Alignment of Surface Sequences

Cited by 66 publications

References 55 publications

Human Shape and Pose Tracking Using Keyframes

Human Shape and Pose Tracking Using Keyframes

4D Match Trees for Non-rigid Surface Alignment

Volumetric Performance Capture from Minimal Camera Viewpoints

Contact Info

Product

Resources

About