Model-based human shape reconstruction from multiple views

Starck, Jonathan; Hilton, Adrian

doi:10.1016/j.cviu.2007.10.001

Cited by 15 publications

(9 citation statements)

References 56 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides, a predefined template model can also be used to reconstruct the motion of an object by deforming it to fit the multi-view video input [3,7,5,6]. Beyond that, a skeleton can be further embedded into the template to better capture kinematic motions of moving objects [24,10,14,21]. Besides color cameras, systems with multiple depth cameras are also proposed in recent years [29,9].…”

Section: Related Workmentioning

confidence: 99%

Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization

Guo

Wang

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

117

118

View full text Add to dashboard Cite

We present a new motion tracking method to robustly reconstruct non-rigid geometries and motions from single view depth inputs captured by a consumer depth sensor. The idea comes from the observation of the existence of intrinsic articulated subspace in most of non-rigid motions. To take advantage of this characteristic, we propose a novel L 0 based motion regularizer with an iterative optimization solver that can implicitly constrain local deformation only on joints with articulated motions, leading to reduced solution space and physical plausible deformations. The L 0 strategy is integrated into the available non-rigid motion tracking pipeline, forming the proposed L 0 -L 2 non-rigid motion tracking method that can adaptively stop the tracking error propagation. Extensive experiments over complex human body motions with occlusions, face and hand motions demonstrate that our approach substantially improves tracking robustness and surface reconstruction accuracy.

show abstract

Section: Related Workmentioning

confidence: 99%

Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization

Guo

Wang

et al. 2015

2015 IEEE International Conference on Computer Vision (ICCV)

117

118

View full text Add to dashboard Cite

show abstract

“…One of the areas in which this marriage is being fertile the most is the one of estimating the 3D shape of an object given an image, or to generate novel views of the same object. Indeed, pre deep learning methods [4,15,20,42,29,35] often need multiple views at test time and rely on the assumption that descriptors can be matched across views [13,1], handling poorly self-occlusions, lack of texture [32] and large viewpoint changes [25]. Conversely, more recent works [37,46,7,36,22,2] are built upon powerful deep learning models trained on virtually infinite synthetic data rendered from ShapeNet [5].…”

Section: Related Workmentioning

confidence: 99%

End-to-End 6-DoF Object Pose Estimation Through Differentiable Rasterization

Palazzi

Bergamini

Calderara

et al. 2019

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Here we introduce an approximated differentiable renderer to refine a 6-DoF pose prediction using only 2D alignment information. To this end, a two-branched convolutional encoder network is employed to jointly estimate the object class and its 6-DoF pose in the scene. We then propose a new formulation of an approximated differentiable renderer to re-project the 3D object on the image according to its predicted pose; in this way the alignment error between the observed and the re-projected object silhouette can be measured. Since the renderer is differentiable, it is possible to back-propagate through it to correct the estimated pose at test time in an online learning fashion. Eventually we show how to leverage the classification branch to profitably re-project a representative model of the predicted class (i.e. a medoid) instead. Each object in the scene is processed independently and novel viewpoints in which both objects arrangement and mutual pose are preserved can be rendered.

show abstract

“…This is then refined by stereo matching using a volumetric graph-cut with silhouette rim constraints [19]. Reconstruction is performed independently at each video time frame resulting in an unstructured mesh sequence with a different number of vertices and mesh connectivity at each frame.…”

Section: Fvvr Pipelinementioning

confidence: 99%

Free-viewpoint video rendering for mobile devices

Imber

Volino

Guillemaut

et al. 2013

Proceedings of the 6th International Conference on Computer Vision / Computer Graphics Collaboration Techniques and Application

Self Cite

View full text Add to dashboard Cite

Free-viewpoint video renderers (FVVR) allow a user to view captured video footage from any position and direction. Despite the obvious appeal of such systems, they have yet to make a major impact on digital entertainment. Current FVVR implementations have been on desktop computers. Media consumption is increasingly through mobile devices, such as smart phones and tablets; adapting FVVR to mobile platforms will open this new form of media up to a wider audience. An efficient, high-quality FVVR, which runs in real time with user interaction on a mobile device, is presented. Performance is comparable to recent desktop implementations. The FVVR supports relighting and integration of relightable free-viewpoint video (FVV) content into computergenerated scenes. A novel approach to relighting FVVR content is presented which does not require prior knowledge of the scene illumination or accurate surface geometry. Surface appearance is separated into a detail component, and a set of materials with properties determining surface colour and specular behaviour. This allows plausible relighting of the dynamic FVV for rendering on mobile devices.

show abstract

Model-based human shape reconstruction from multiple views

Cited by 15 publications

References 56 publications

Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization

Robust Non-rigid Motion Tracking and Surface Reconstruction Using L0 Regularization

End-to-End 6-DoF Object Pose Estimation Through Differentiable Rasterization

Free-viewpoint video rendering for mobile devices

Contact Info

Product

Resources

About