Hanbyel Cho

I recently earned my PhD in Electrical Engineering from KAIST, where I was advised by Prof. Junmo Kim. I previously obtained my MS (2020) and BS (2018) in Electrical Engineering from KAIST.

My doctoral research focused on capturing and reconstructing human-related subjects—such as body pose and shape—under real-world conditions for practical applications in immersive environments. In particular, I investigated human body joint estimation in camera lens distortion scenarios and human body mesh reconstruction in the presence of ambiguities, such as occlusion.

During my PhD studies, I gained valuable experience through two internships at Meta Reality Labs—one in Pittsburgh, PA, USA (2023), and another in Redmond, WA, USA (2024). I was also honored to be selected as a finalist for the Qualcomm Innovation Fellowship in both 2022 and 2023.

If you're interested in collaborating, feel free to reach out!

tlrl4658 [at] gmail.com /  CV  /  Bio  /  Scholar  /  Linkedin  /  Github

Publications

I’m interested in computer vision/graphics, deep learning, and generative AI. My work primarily focuses on 3D human understanding—covering faces, body poses, and shapes—and I also explore 4D generation in a separate line of research. Below are my recent publications; some papers are highlighted.

Efficient 4D dynamic scene editing method using 4D Gaussian Splatting, focusing on static 3D Gaussians and score distillation refinement to achieve faster, high-quality edits.

Proposes a novel loss-aware vulnerability proxy (LAVP) for gradient inversion attacks in federated learning, using the maximum or minimum eigenvalue of the Hessian to capture sample vulnerabilities beyond traditional gradient norm.

Proposes a novel generative framework for 3D human mesh recovery, leveraging denoising diffusion to model multiple plausible outcomes and address the inherent ambiguity in the task.

Leveraging neural feature fields to render multi-view feature maps and enforcing cross-view consistency enables accurate 3D human mesh recovery from a single image.

Replacing naive GRU-based modeling with a Vision Transformer and a learnable Channel Rearranging Matrix reduces motion fragmentation, boosting human mesh recovery accuracy, robustness, and efficiency.

Masked face recognition approach that leverages multi-focal spatial attention to precisely isolate unmasked features.

Replacing softmax in non-local blocks with a simple scaling factor mitigates its over-reliance on vector magnitude, thereby improving performance, robustness, and efficiency.

3D human pose estimation model that leverages MAML and synthetic distorted data to rapidly adapt to various camera distortions without requiring calibration.

Introduces a novel Convolutional Unit that aligns whitening theory with convolutional architectures, significantly boosting the stability and performance of Batch Whitening.

Stochastic modeling-based face super-resolution method that separates deterministic and stochastic attributes to reduce uncertainty and improve reconstruction quality.