Seunghyeon Seo

I'm a Ph.D. candidate at College of Engineering in Seoul National University, where I'm advised by Prof. Nojun Kwak in the Machine Intelligence and Pattern Analysis Lab (MIPAL). Previously, I got my bachelor's degree from College of Agriculture and Life Sciences in SNU, where I majored in Agricultural Economics.

I'm interested in computer vision, deep learning, and neural rendering. Much of my interest is currently focused on the efficient training framework of NeRF/3D-GS and synthetic data training leveraging diffusion models.

Currently on the hunt for an internship/full-time position! If you're interested, please don't hesitate to reach out. Thanks! 🌟

Email  /  CV  /  Google Scholar  /  LinkedIn  /  Github

Mar. 2025: One paper is accepted to CVPR 2025 Workshop on Computer Vision for Metaverse.

Feb. 2025: I'll be heading back to Meta Reality Labs this summer for another round as a research scientist intern!

Sep. 2024: I have been acknowledged as an outstanding reviewer for ECCV 2024.

Apr. 2024: One paper is accepted to CVPR 2024 Workshop on Efficient Large Vision Models.

Feb. 2024: I will be joining Meta Reality Labs as a research scientist intern this summer.

We introduce a 3D object extraction method for Gaussian Splatting that prunes irrelevant primitives using K-nearest neighbors analysis and compensates for occlusions with diffusion-based generative inpainting.

We propose surface-sphere augmentation to preserve camera-to-surface distances for consistent ray filtering and inner-sphere augmentation to randomize viewpoints, improving both diversity and consistency.

We present ARC-NeRF, leveraging Area Ray casting to cover broader unseen views with a single ray and adaptive high-frequency regularization. Additionally, luminance consistency regularization uses relative luminance as 'free lunch' data to improve texture accuracy.

We leverage the pre-trained multimodal model CLIP to achieve state-of-the-art performance in video highlight detection by fine-tuning the encoder and integrating a novel saliency pooling technique.

We simplify outdoor scene relighting for NeRF by aligning with the sun, eliminating the need for environment maps and speeding up the process using a novel cubemap concept within the framework of TensoRF.

We expedite ViT inference by concatenating abstract visual tokens from multiple images along dim=1 and processing them collectively.

We utilize the flipped reflection rays as additional training resources for the few-shot novel view synthesis, leading to more accurate surface normal estimation.

We model the high-dimensional joint distribution of human keypoints with a mixture density model by Random Keypoint Grouping strategy and achieve competitive performance working in real-time by eliminating additional instance identification process.

We propose the end-to-end multi-object Detection with a Regularized Mixture Model (D-RMM), which is trained by minimizing the NLL with the proposed regularization term, maximum component maximization (MCM) loss, preventing duplicate predictions.

We model a ray with mixture density model, leading to efficient learning of density distribution with sparse inputs, and propose an effective auxiliary task of ray depth estimation for few-shot novel view synthesis.

We introduce a simple yet effective data augmentation method, Mix/UnMix (MUM), which unmixes feature tiles for the mixed image tiles for the SSOD framework.

Thanks for sharing the website template, Jon Barron. :)