SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2304.05690 · 2023

HybrIK-X: Hybrid Analytical-Neural Inverse Kinematics for Whole-body Mesh Recovery

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 0 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.

RepositoryRoleRan
Jeff-sjtu/HybrIK canonical 0 of 8
FunctionStatusWhere it lives
flip Not yet run Jeff-sjtu/HybrIK/hybrik/models/HRNetSMPLXCamKid.py
code served (permissive licence) · get_code("fabada0c3f6b8840")
focalLength_mm2px Not yet run Jeff-sjtu/HybrIK/hybrik/datasets/agora_smplx.py
code served (permissive licence) · get_code("ed832a8183efcc97")
get_focal Not yet run Jeff-sjtu/HybrIK/hybrik/datasets/agora_smplx.py
code served (permissive licence) · get_code("733d8811b481fdbe")
norm_heatmap Not yet run Jeff-sjtu/HybrIK/hybrik/models/HRNetSMPLXCamKid.py
code served (permissive licence) · get_code("0635936243f338d5")
norm_heatmap Not yet run Jeff-sjtu/HybrIK/hybrik/models/simple3dposeBaseSMPL.py
code served (permissive licence) · get_code("a828d7ddc0f76aac")
project Not yet run Jeff-sjtu/HybrIK/hybrik/datasets/agora_smplx.py
code served (permissive licence) · get_code("8cc86609ecbd6234")
weighted_l1_loss Not yet run Jeff-sjtu/HybrIK/hybrik/models/criterion.py
code served (permissive licence) · get_code("3b94245b39283e5c")
weighted_laplace_loss Not yet run Jeff-sjtu/HybrIK/hybrik/models/criterion.py
code served (permissive licence) · get_code("86dec2a5c79f02f6")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recovering whole-body mesh by inferring the abstract pose and shape parameters from visual content can obtain 3D bodies with realistic structures. However, the inferring process is highly non-linear and suffers from image-mesh misalignment, resulting in inaccurate reconstruction. In contrast, 3D keypoint estimation methods utilize the volumetric representation to achieve pixel-level accuracy but may predict unrealistic body structures. To address these issues, this paper presents a novel hybrid inverse kinematics solution, HybrIK, that integrates the merits of 3D keypoint estimation and body mesh recovery in a unified framework. HybrIK directly transforms accurate 3D joints to body-part rotations via twist-and-swing decomposition. The swing rotations are analytically solved with 3D joints, while the twist rotations are derived from visual cues through neural networks. To capture comprehensive whole-body details, we further develop a holistic framework, HybrIK-X, which enhances HybrIK with articulated hands and an expressive face. HybrIK-X is fast and accurate by solving the whole-body pose with a one-stage model. Experiments demonstrate that HybrIK and HybrIK-X preserve both the accuracy of 3D joints and the realistic structure of the parametric human model, leading to pixel-aligned whole-body mesh recovery. The proposed method significantly surpasses the state-of-the-art methods on various benchmarks for body-only, hand-only, and whole-body scenarios. Code and results can be found at https://jeffli.site/HybrIK-X/

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2304.05690")
get_code_for_paper("2304.05690")
have("2304.05690")

Connect an agent — have() is free.