# GenCape: Structure-Inductive Generative Modeling for Category-Agnostic Pose Estimation

arXiv: https://arxiv.org/abs/2605.13151 · HTML: https://mlsanity.com/paper/2605.13151/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 26 of its 37 references that are in the map.
- First posted on arXiv 13 May 2026.

## Builds on (most cited first, 26 of 26)

- [Variational Graph Auto-Encoders](https://mlsanity.com/paper/1611.07308/) (2016)
- [Deep High-Resolution Representation Learning for Human Pose Estimation](https://mlsanity.com/paper/1902.09212/) (2019)
- [Swin Transformer V2: Scaling Up Capacity and Resolution](https://mlsanity.com/paper/2111.09883/) (2021)
- [ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation](https://mlsanity.com/paper/2204.12484/) (2022)
- [Deep Learning-Based Human Pose Estimation: A Survey](https://mlsanity.com/paper/2012.13392/) (2020)
- [AP-10K: A Benchmark for Animal Pose Estimation in the Wild](https://mlsanity.com/paper/2108.12617/) (2021)
- [Hierarchical Diffusion Policy for Kinematics-Aware Multi-Task Robotic Manipulation](https://mlsanity.com/paper/2403.03890/) (2024)
- [SuperAnimal pretrained pose estimation models for behavioral analysis](https://mlsanity.com/paper/2203.07436/) (2022)
- [Pose for Everything: Towards Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2207.10387/) (2022)
- [A Survey of Embodied Learning for Object-Centric Robotic Manipulation](https://mlsanity.com/paper/2408.11537/) (2024)
- [Graph-PCNN: Two Stage Human Pose Estimation with Graph Pose Refinement](https://mlsanity.com/paper/2007.10599/) (2020)
- [CLAMP: Prompt-based Contrastive Learning for Connecting Language and Animal Pose](https://mlsanity.com/paper/2206.11752/) (2022)
- [X-Pose: Detecting Any Keypoints](https://mlsanity.com/paper/2310.08530/) (2023)
- [A Graph-Based Approach for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2311.17891/) (2023)
- [Regular Splitting Graph Network for 3D Human Pose Estimation](https://mlsanity.com/paper/2305.05785/) (2023)
- [CapeX: Category-Agnostic Pose Estimation from Textual Point Explanation](https://mlsanity.com/paper/2406.00384/) (2024)
- [Capturing the motion of every joint: 3D human pose and shape estimation with independent tokens](https://mlsanity.com/paper/2303.00298/) (2023)
- [OpenKD: Opening Prompt Diversity for Zero- and Few-shot Keypoint Detection](https://mlsanity.com/paper/2409.19899/) (2024)
- [Meta-Point Learning and Refining for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2403.13647/) (2024)
- [SCAPE: A Simple and Strong Category-Agnostic Pose Estimator](https://mlsanity.com/paper/2407.13483/) (2024)
- [V-VIPE: Variational View Invariant Pose Embedding](https://mlsanity.com/paper/2407.07092/) (2024)
- [Learning Structure-Supporting Dependencies via Keypoint Interactive Transformer for General Mammal Pose Estimation](https://mlsanity.com/paper/2502.18214/) (2025)
- [Probabilistic Prompt Distribution Learning for Animal Pose Estimation](https://mlsanity.com/paper/2503.16120/) (2025)
- [CapeLLM: Support-Free Category-Agnostic Pose Estimation with Multimodal Large Language Models](https://mlsanity.com/paper/2411.06869/) (2024)
- [Recurrent Feature Mining and Keypoint Mixup Padding for Category-Agnostic Pose Estimation](https://mlsanity.com/paper/2503.21140/) (2025)
- [CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation](https://mlsanity.com/paper/2410.09010/) (2024)

## Abstract (arXiv)

Category-agnostic pose estimation (CAPE) aims to localize keypoints on query images from arbitrary categories, using only a few annotated support examples for guidance. Recent approaches either treat keypoints as isolated entities or rely on manually defined skeleton priors, which are costly to annotate and inherently inflexible across diverse categories. Such oversimplification limits the model's capacity to capture instance-wise structural cues critical for accurate pixel-level localization. To overcome these limitations, we propose GenCape, a Generative-based framework for CAPE that infers keypoint relationships solely from image-based support inputs, without additional textual descriptions or predefined skeletons. Our framework consists of two principal components: an iterative Structure-aware Variational Autoencoder (i-SVAE) and a Compositional Graph Transfer (CGT) module. The former infers soft, instance-specific adjacency matrices from support features through variational inference, embedded layer-wise into the Graph Transformer Decoder for progressive structural priors refinement. The latter adaptively aggregates multiple latent graphs into a query-aware structure via Bayesian fusion and attention-based reweighting, enhancing resilience to visual uncertainty and support-induced bias. This structure-aware design facilitates effective message propagation among keypoints and promotes semantic alignment across object categories with diverse keypoint topologies. Experimental results on the MP-100 dataset show that our method achieves substantial gains over graph-support baselines under both 1- and 5-shot settings, while maintaining competitive performance against text-support counterparts.