FlexiAvatar Accepted
Our collaborative work on visibility-aware 3D Gaussian human avatar reconstruction has been accepted to ECCV 2026.
MD Khalequzzaman Chowdhury Sayem
3D AI Engineer at LIOPS · Researcher in 3D Vision and Multimodal AI
I am a 3D AI Engineer at LIOPS, where I work on stereo depth estimation for 3D AI and vision systems. My research background comes from the Vision & Learning Lab at UNIST, where I worked under the supervision of Prof. Seungryul Baek and Prof. Binod Bhattarai. My research focuses on multimodal learning and vision-language models, with an emphasis on structured and grounded reasoning in complex visual environments, particularly involving articulated hands and human-object interactions.
My recent work develops large-scale benchmarks and real-time Transformer architectures that integrate explicit 3D geometric supervision into multimodal models, improving fine-grained spatial reasoning reliability and cross-task generalization.
I am currently interested in advancing multimodal foundation models toward more reliable and interpretable reasoning, and in translating 3D perception research into practical depth-estimation systems, with long-term directions in grounded world models and embodied multimodal systems that integrate perception, language, and action.
I am always open to collaborations and discussions. If you are interested in my research or have any inquiries, feel free to reach out to me at khalequzzamansayem@gmail.com.
