Bio

I am Juil Koo, a second-year PhD student in the KAIST Visual AI Group, led by Prof. Minhyuk Sung. In summer 2024, I interned at Adobe Research, closely collaborating with Duygu Ceylan, Paul Guerrero and Chun-Hao Huang.

My research interests primarily revolve around stochastic differential equations and 3D geometry. Recently, I've been focusing on understanding the underlying fundamentals of diffusion models and leveraging their rich priors to unlock their potential in diverse applications. Prior to this, I mainly worked on the intersection between 3D geometry and language. I aim to address practical problems through theoretical insights.

My Erdős number is 3 (Juil Koo → Leonidas Guibas → Frances Yao → Paul Erdős).

3D Gallery

News

• (Sep. 2024) Two papers are accepted at NeurIPS 2024: SyncTweedies and NeuralPose.
• (Aug. 2024) Posterior Distillation Sampling received the Best Paper Award at the 2024 Samsung Electronics DS-KAIST R&D Exchange Meeting.
• (Jun. 2024) Posterior Distillation Sampling is presented in six workshops at CVPR 2024: 3DMV, M3DS, AI4CC, AI3DG, CVEU, and GCV.
• (Mar. 2024) I start my internship at Adobe Research in London.
• (Feb. 2024) Posterior Distillation Sampling has been accepted at CVPR 2024!
• (Sep. 2023) I presented a brief overview of SALAD at two workshops during ICCV 2023: Language for 3D Scenes (L3DS) and AI for 3D Content Creation (AI3DCC).
• (Jul. 2023) Our SALAD paper got accepted to ICCV 2023!
• (Jun. 2023) PartGlot is featured in the KAIST R&D Annual Report as a research highlight.
• (Feb. 2023) I received an outstanding TA award.
• (Feb. 2023) My Master's thesis has been awarded the outstanding thesis award!
• (Dec. 2022) I passed my Master's thesis defense.
• (Nov. 2022) Our PartGlot paper won the Qualcomm Innovation Fellowship Korea (QIFK) 2022!
• (Oct. 2022) I made a short presentation about PartGlot at the ECCV 2022 Language for 3D Scenes (L3DS) Workshop.
• (Jul. 2022) I won an outstanding paper award at Korea Computer Graphics Society (KCGS 2022).
• (Mar. 2022) My first work, PartGlot, has been accepted as an oral paper at CVPR 2022. Thank all my valuable collaborators for this huge accomplishment!
• (Feb. 2022) I received an outstanding TA award.

Show All

Publications

SyncTweedies: A General Generative Framework Based on Synchronized Diffusions

Jaihoon Kim*, Juil Koo*, Kyeongmin Yeo*, Minhyuk Sung (* co-first author.) NeurIPS 2024 [Project] [Paper] [Code]

Neural Pose Representation Learning for Generating and Transferring Non-Rigid Object Poses

Seungwoo Yoo, Juil Koo, Kyeongmin Yeo, Minhyuk Sung NeurIPS 2024 [Paper]

Posterior Distillation Sampling

Juil Koo, Chanho Park, Minhyuk Sung CVPR 2024 [Project] [Paper] [Code] [Video]

SALAD: Part-Level Latent Diffusion for 3D Shape Generation and Manipulation

Juil Koo*, Seungwoo Yoo*, Minh Hieu Nguyen*, Minhyuk Sung (* co-first author.) ICCV 2023 [Project] [Paper] [Code]

PartGlot: Learning Shape Part Segmentation from Language Reference Games

Juil Koo, Ian Huang, Panos Achlioptas, Leonidas Guibas, Minhyuk Sung CVPR 2022 (Oral) [Project] [Paper] [Code] [Video]

Academic Service

Conference Reviewer: CVPR, ICCV, ECCV, AAAI, Euroghraphics

Workshop Reviewer: GCV@CVPR2024, AI4VA@ECCV2024, OOD-CV@ECCV2024