Generating Key Postures of Bharatanatyam Adavus with Pose Estimation

arXiv cs.CV / 4/1/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper addresses the challenge of digitally preserving Bharatanatyam by generating codified adavus and their precise key postures without losing anatomical or stylistic fidelity.
It proposes a pose-aware generative framework that integrates pose estimation and uses keypoint-based losses plus pose-consistency constraints to guide synthesis.
The models are conditioned on key posture class labels, and experiments compare cGAN and conditional diffusion variants with and without pose supervision.
Results indicate that adding pose supervision substantially improves realism, quality, and cultural authenticity by better aligning generated poses with ground-truth keypoint structures.
The authors position the approach as scalable for digital preservation, education, and global dissemination, and provide code via a public GitHub repository.

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.