Generating Key Postures of Bharatanatyam Adavus with Pose Estimation

2026-03-31

AI Summary

This study addresses the challenge of high-fidelity generation of key poses in Bharatanatyam, a classical Indian dance form, in the digital era. The authors propose a conditional generative framework that integrates pose estimation by combining conditional generative adversarial networks (cGANs) with conditional diffusion models. The approach introduces keypoint loss and pose consistency constraints, marking the first application of pose-aware supervision to traditional dance pose synthesis. Experimental results demonstrate that the proposed framework significantly enhances both anatomical accuracy and cultural stylistic authenticity in the generated poses. This advancement offers a scalable and high-fidelity technical pathway for the digital preservation, pedagogy, and global dissemination of Bharatanatyam.

Abstract

Preserving intangible cultural dances rooted in centuries of tradition and governed by strict structural and symbolic rules presents unique challenges in the digital era. Among these, Bharatanatyam, a classical Indian dance form, stands out for its emphasis on codified adavus and precise key postures. Accurately generating these postures is crucial not only for maintaining anatomical and stylistic integrity, but also for enabling effective documentation, analysis, and transmission to broader global audiences through digital means. We propose a pose-aware generative framework integrated with a pose estimation module, guided by keypoint-based loss and pose consistency constraints. These supervisory signals ensure anatomical accuracy and stylistic integrity in the synthesized outputs. We evaluate four configurations: standard conditional generative adversarial network (cGAN), cGAN with pose supervision, conditional diffusion, and conditional diffusion with pose supervision. Each model is conditioned on key posture class labels and optimized to maintain geometric structure. In both cGAN and conditional diffusion settings, the integrated pose guidance aligns generated poses with ground-truth keypoint structures, promoting cultural fidelity. Our results demonstrate that incorporating pose supervision significantly enhances the quality, realism, and authenticity of generated Bharatanatyam postures. This framework provides a scalable approach for the digital preservation, education, and dissemination of traditional dance forms, enabling high-fidelity generation without compromising cultural precision. Code is available at https://github.com/jagidsh/Generating-Key-Postures-of-Bharatanatyam-Adavus-with-Pose-Estimation.

Problem

• Bharatanatyam
• key postures
• adavus
• digital preservation
• pose generation

Innovation

• pose-aware generation
• keypoint-based loss
• pose consistency constraints
• conditional diffusion
• cultural fidelity