Kiran Chhatre

I am an MSCA ITN Ph.D. fellow at the KTH Royal Institute of Technology, advised by Christopher Peters, and currently a Research Scientist Intern at Meta working on world models. During my Ph.D., I have collaborated with Michael J. Black, Timo Bolkart, Srikrishna Karanam, Paul Guerrero, and Chun-Hao Paul Huang, and completed research internships at Adobe Research, Sony Research, Electronic Arts SEED, and Ubisoft La Forge. I was also a Guest Scientist at the Max Planck Institute for Intelligent Systems.

Before my Ph.D., I worked as a Research Affiliate with the BEAM team at Lawrence Berkeley National Laboratory. I received my M.Sc. in Mechanical Engineering from RWTH Aachen University, where I worked with Mikhail Itskov and interned at IBM Research, Dassault Systèmes SIMULIA, and ITA Technologietransfer. I received my B.Tech. in Mechanical Engineering from COEP Technological University.

/ Resume / Scholar / LinkedIn / GitHub / Hugging Face / X

Research

My research lies at the intersection of computer vision, generative AI, and world models. I work on video generation and editing, multimodal learning, 3D vision, human motion generation, and evaluation of foundation models.

My goal is to build models that understand people, objects, interactions, and how scenes evolve over time. My recent work includes social world models, controllable video generation, dense video understanding, physics-based synthetic data, and speech-driven 3D body animation.

	TrajectoryMover: Generative Movement of Object Trajectories in Videos Kiran Chhatre, Hyeonho Jeong, Yulia Gryaditskaya, Christopher E. Peters, Chun-Hao Paul Huang, Paul Guerrero arXiv preprint, 2026 arxiv / website / code / @misc{chhatre2026trajectorymovergenerativemovementobject, title={TrajectoryMover: Generative Movement of Object Trajectories in Videos}, author={Kiran Chhatre and Hyeonho Jeong and Yulia Gryaditskaya and Christopher E. Peters and Chun-Hao Paul Huang and Paul Guerrero}, year={2026}, eprint={2603.29092}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2603.29092}, } A scene-aware video editing method that moves an object to a new starting position while generating a plausible new trajectory and preserving the surrounding scene.
	Spectrum: Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts Kiran Chhatre, Christopher Peters, Srikrishna Karanam Association for the Advancement of Artificial Intelligence (AAAI), 2026 arxiv / website / poster / x thread / patent / @misc{chhatre2025learning3dtextureawarerepresentations, title={Learning {3D} Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts}, author={Kiran Chhatre and Christopher Peters and Srikrishna Karanam}, year={2025}, eprint={2508.06032}, archivePrefix={arXiv}, primaryClass={cs.CV}, url={https://arxiv.org/abs/2508.06032}, } A 3D texture-aware diffusion representation for open-vocabulary parsing of clothing and body parts across diverse poses, outfits, and multi-person scenes.
	AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion Kiran Chhatre, Radek Daněček, Nikos Athanasiou, Giorgio Becherini, Christopher Peters, Michael J. Black, Timo Bolkart IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2024 arxiv / website / youtube / code / poster / x thread / @InProceedings{Chhatre_2024_CVPR, author = {Chhatre, Kiran and Daněček, Radek and Athanasiou, Nikos and Becherini, Giorgio and Peters, Christopher and Black, Michael J. and Bolkart, Timo}, title = {AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion}, booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)}, month = {June}, year = {2024}, pages = {1942-1953}, url = {https://amuse.is.tue.mpg.de}, } A latent-diffusion model for generating controllable emotional 3D body motion directly from speech.
	Audiopedia: Audio QA with Knowledgeoral Abhirama S. Penamakuri, Kiran Chhatre*, Akshat Jain ( denotes equal contribution) IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2025 arxiv / website / code / @INPROCEEDINGS{10889814, author={Penamakuri, Abhirama Subramanyam and Chhatre, Kiran and Jain, Akshat}, booktitle={ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)}, title={Audiopedia: Audio QA with Knowledge}, year={2025}, volume={}, number={}, pages={1-5}, keywords={Adaptation models;Benchmark testing;Signal processing;Question answering (information retrieval);Cognition;Acoustics;Speech processing;audio question answering;knowledge-intensive questions;audio entity linking}, doi={10.1109/ICASSP49660.2025.10889814}} A knowledge-intensive audio question-answering benchmark and method that improves audio-language models using external knowledge.
	EMOTE: Emotional Speech-Driven Animation with Content-Emotion Disentanglement Radek Daněček, Kiran Chhatre, Shashank Tripathi, Yandong Wen, Michael J. Black, Timo Bolkart ACM SIGGRAPH Asia Conference Papers, 2023 arxiv / website / video / code / x thread / @inproceedings{10.1145/3610548.3618183, author = {Dan\v{e}\v{c}ek, Radek and Chhatre, Kiran and Tripathi, Shashank and Wen, Yandong and Black, Michael and Bolkart, Timo}, title = {Emotional Speech-Driven Animation with Content-Emotion Disentanglement}, year = {2023}, isbn = {9798400703157}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3610548.3618183}, doi = {10.1145/3610548.3618183}, booktitle = {SIGGRAPH Asia 2023 Conference Papers}, articleno = {41}, numpages = {13}, keywords = {Computer Graphics, Computer Vision, Deep learning, Facial Animation, Speech-driven Animation}, location = {Sydney, NSW, Australia}, series = {SA '23} } A speech-driven 3D facial animation method that generates synchronized and emotionally expressive facial motion from audio and an emotion label.

View all research / Full academic CV

Academic Services

Reviewer: CVPR, ICCV, ECCV, NeurIPS, ICLR, SIGGRAPH, SIGGRAPH Asia, TOG, and TVCG.

Updated on: 2026-07-12

Thanks, Jon Barron!

Kiran Chhatre

Research

TrajectoryMover: Generative Movement of Object Trajectories in Videos

Spectrum: Learning 3D Texture-Aware Representations for Parsing Diverse Human Clothing and Body Parts

AMUSE: Emotional Speech-driven 3D Body Animation via Disentangled Latent Diffusion

Audiopedia: Audio QA with Knowledgeoral

EMOTE: Emotional Speech-Driven Animation with Content-Emotion Disentanglement

Academic Services