ICON: Implicit Clothed humans Obtained from Normals

Xiu, Yuliang; Yang, Jinlong; Tzionas, Dimitrios; Black, Michael J.

doi:10.48550/arxiv.2112.09127

Cited by 3 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PHORHUM [2] modifies the geometric representation to SDF to get finer geometry and normal, so they can simultaneously estimate detailed 3D geometry and the unshaded surface color together with the scene illumination. ICON [37] infers a 3D clothed human meshes from a color image by utilizing a body-guided normal prediction model and a local-featurebased implicit 3D representation conditioned on SMPL(-X). SelfRecon [11] represents the human body as a template mesh and SDF in canonical space and utilizes a deformation field consisting of rigid forward LBS deformation and small non-rigid deformation to generate correspondences.…”

Section: Related Workmentioning

confidence: 99%

“…For each object in these datasets, we adopt SelfRecon [11] to reconstruct the highfidelity surface to better aggregate the information across frames. Some generated models, such as ICON [37] can do the same much faster but with less precision.…”

Section: Datasetmentioning

confidence: 99%

“…Moreover, our data preparation takes a long to process if we require a more accurate human surface as input, such as SelfRecon. However, we believe that this problem will be solved as the accuracy and speed of human shape reconstruction methods have already been greatly improved [2,37].…”

Section: Limitation and Future Workmentioning

confidence: 99%

See 2 more Smart Citations

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

Peng¹,

Hu²,

Zhou³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Datasetmentioning

confidence: 99%

See 1 more Smart Citation

SelfNeRF: Fast Training NeRF for Human from Monocular Self-rotating Video

Peng¹,

Hu²,

Zhou³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Recently, some monocular human reconstruction approaches based on implicit neural representation have demonstrated compelling results [10,20,21,23,41,42,46,50,55,56]. These methods can handle various topologies, and thus can represent various clothing and hairstyles.…”

Section: Introductionmentioning

confidence: 99%

SelfRecon: Self Reconstruction Your Digital Avatar from Monocular Video

Jiang¹,

Ye²,

Bao³

et al. 2022

Preprint

View full text Add to dashboard Cite

We propose SelfRecon, a clothed human body reconstruction method that combines implicit and explicit representations to recover space-time coherent geometries from a monocular self-rotating human video. Explicit methods require a predefined template mesh for a given sequence, while the template is hard to acquire for a specific subject. Meanwhile, the fixed topology limits the reconstruction accuracy and clothing types. Implicit methods support arbitrary topology and have high quality due to continuous geometric representation. However, it is difficult to integrate multi-frame information to produce a consistent registration sequence for downstream applications. We propose to combine the advantages of both representations. We utilize differential mask loss of the explicit mesh to obtain the coherent overall shape, while the details on the implicit surface are refined with the differentiable neural rendering. Meanwhile, the explicit mesh is updated periodically to adjust its topology changes, and a consistency loss is designed to match both representations closely. Compared with existing methods, SelfRecon can produce high-fidelity surfaces for arbitrary clothed humans with self-supervised optimization. Extensive experimental results demonstrate its effectiveness on real captured monocular videos.

show abstract