Function4D: Real-time Human Volumetric Capturefrom Very Sparse Consumer RGBD Sensors

[CVPR 2021 Oral Paper]
Function4D: Real-time Human Volumetric Capture from Very Sparse Consumer RGBD Sensors

Abstract:
Human volumetric capture is a long-standing topic in computer vision and computer graphics. Although high-quality results can be achieved using sophisticated off-line systems, real-time human volumetric capture of complex scenarios, especially using light-weight setups, remains challenging. In this paper, we propose a human volumetric capture method that combines temporal volumetric fusion and deep implicit functions. To achieve high-quality and temporal-continuous reconstruction, we propose dynamic sliding fusion to fuse neighboring depth observations together with topology consistency. Moreover, for detailed and complete surface generation, we propose detail-preserving deep implicit functions for RGBD input which can not only preserve the geometric details on the depth inputs but also generate more plausible texturing results. Results and experiments show that our method outperforms existing methods in terms of view sparsity, generalization capacity, reconstruction quality, and run-time efficiency.

[changtimwu]

Amazing. Do you mind sharing the model of RGBD camera you use in this paper? I believe this could be further applied to non-ToF RGBD cameras, which are dirt cheap nowadays.

[PeopleVersusTV]

Really amazing! Are there any plans for release of your software?