# KITRO: Refining Human Mesh by 2D Clues and Kinematic-tree Rotation arXiv: https://arxiv.org/abs/2405.19833 ยท HTML: https://mlsanity.com/paper/2405.19833/ ## Key facts - Cited by 5 papers in the map (data through 14 Oct 2026). - Builds on 33 of its 40 references that are in the map. - First posted on arXiv 30 May 2024. ## Builds on (most cited first, 30 of 33) - [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017) - [Deep High-Resolution Representation Learning for Visual Recognition](https://mlsanity.com/paper/1908.07919/) (2019) - [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019) - [Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields](https://mlsanity.com/paper/1611.08050/) (2016) - [End-to-end Recovery of Human Shape and Pose](https://mlsanity.com/paper/1712.06584/) (2017) - [Keep it SMPL: Automatic Estimation of 3D Human Pose and Shape from a Single Image](https://mlsanity.com/paper/1607.08128/) (2016) - [Learning to Reconstruct 3D Human Pose and Shape via Model-fitting in the Loop](https://mlsanity.com/paper/1909.12828/) (2019) - [VIBE: Video Inference for Human Body Pose and Shape Estimation](https://mlsanity.com/paper/1912.05656/) (2019) - [PIFuHD: Multi-Level Pixel-Aligned Implicit Function for High-Resolution 3D Human Digitization](https://mlsanity.com/paper/2004.00452/) (2020) - [End-to-End Human Pose and Mesh Reconstruction with Transformers](https://mlsanity.com/paper/2012.09760/) (2020) - [PARE: Part Attention Regressor for 3D Human Body Estimation](https://mlsanity.com/paper/2104.08527/) (2021) - [HybrIK: A Hybrid Analytical-Neural Inverse Kinematics Solution for 3D Human Pose and Shape Estimation](https://mlsanity.com/paper/2011.14672/) (2020) - [I2L-MeshNet: Image-to-Lixel Prediction Network for Accurate 3D Human Pose and Mesh Estimation from a Single RGB Image](https://mlsanity.com/paper/2008.03713/) (2020) - [Mesh Graphormer](https://mlsanity.com/paper/2104.00272/) (2021) - [Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose](https://mlsanity.com/paper/2008.09047/) (2020) - [CLIFF: Carrying Location Information in Full Frames into Human Pose and Shape Estimation](https://mlsanity.com/paper/2208.00571/) (2022) - [Beyond Static Features for Temporally Consistent 3D Human Pose and Shape from a Video](https://mlsanity.com/paper/2011.08627/) (2020) - [BodyNet: Volumetric Inference of 3D Human Body Shapes](https://mlsanity.com/paper/1804.04875/) (2018) - [SPEC: Seeing People in the Wild with an Estimated Camera](https://mlsanity.com/paper/2110.00620/) (2021) - [Graph Stacked Hourglass Networks for 3D Human Pose Estimation](https://mlsanity.com/paper/2103.16385/) (2021) - [On Self-Contact and Human Pose](https://mlsanity.com/paper/2104.03176/) (2021) - [Synthetic Training for Accurate 3D Human Pose and Shape Estimation in the Wild](https://mlsanity.com/paper/2009.10013/) (2020) - [Cascaded deep monocular 3D human pose estimation with evolutionary training data](https://mlsanity.com/paper/2006.07778/) (2020) - [NeuralAnnot: Neural Annotator for 3D Human Mesh Training Sets](https://mlsanity.com/paper/2011.11232/) (2020) - [Zolly: Zoom Focal Length Correctly for Perspective-Distorted Human Mesh Reconstruction](https://mlsanity.com/paper/2303.13796/) (2023) - [Delving Deep Into Hybrid Annotations for 3D Human Recovery in the Wild](https://mlsanity.com/paper/1908.06442/) (2019) - [Beyond Weak Perspective for Monocular 3D Human Pose Estimation](https://mlsanity.com/paper/2009.06549/) (2020) - [Out-of-Domain Human Mesh Reconstruction via Dynamic Bilevel Online Adaptation](https://mlsanity.com/paper/2111.04017/) (2021) - [DenseBody: Directly Regressing Dense 3D Human Pose and Shape From a Single Color Image](https://mlsanity.com/paper/1903.10153/) (2019) - [On the Calibration of Human Pose Estimation](https://mlsanity.com/paper/2311.17105/) (2023) ## Built on by (most cited first, 5 of 5) - [Humans as Checkerboards: Calibrating Camera Motion Scale for World-Coordinate Human Mesh Recovery](https://mlsanity.com/paper/2407.00574/) (2024) - [FastHMR: Accelerating Human Mesh Recovery via Token and Layer Merging with Diffusion Decoding](https://mlsanity.com/paper/2510.10868/) (2025) - [Online Test-time Adaptation for 3D Human Pose Estimation: A Practical Perspective with Estimated 2D Poses](https://mlsanity.com/paper/2503.11194/) (2025) - [PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation](https://mlsanity.com/paper/2505.17475/) (2025) - [EA-RAS: Towards Efficient and Accurate End-to-End Reconstruction of Anatomical Skeleton](https://mlsanity.com/paper/2409.01555/) (2024) ## Abstract (arXiv) 2D keypoints are commonly used as an additional cue to refine estimated 3D human meshes. Current methods optimize the pose and shape parameters with a reprojection loss on the provided 2D keypoints. Such an approach, while simple and intuitive, has limited effectiveness because the optimal solution is hard to find in ambiguous parameter space and may sacrifice depth. Additionally, divergent gradients from distal joints complicate and deviate the refinement of proximal joints in the kinematic chain. To address these, we introduce Kinematic-Tree Rotation (KITRO), a novel mesh refinement strategy that explicitly models depth and human kinematic-tree structure. KITRO treats refinement from a bone-wise perspective. Unlike previous methods which perform gradient-based optimizations, our method calculates bone directions in closed form. By accounting for the 2D pose, bone length, and parent joint's depth, the calculation results in two possible directions for each child joint. We then use a decision tree to trace binary choices for all bones along the human skeleton's kinematic-tree to select the most probable hypothesis. Our experiments across various datasets and baseline models demonstrate that KITRO significantly improves 3D joint estimation accuracy and achieves an ideal 2D fit simultaneously. Our code available at: https://github.com/MartaYang/KITRO.