On November 4th, our lab visited the Chrysanthemum Festival at Yurim Park. We strolled among the fully bloomed chrysanthemums, enjoying relaxed conversations and a refreshing break. Afterward, we shared lunch together, strengthening our team bonds. It was a meaningful outing, made even more special by the chance to connect and enjoy time with everyone in the lab.
Our lab alumnus, Prof. Bochang Moon, conducted a seminar on October 14, 2024, in the undergraduate graphics class, presenting his paper “Target-Aware Image Denoising for Inverse Monte Carlo Rendering.” This study develops a target-aware image denoiser to address the noise issue in scene parameter inference through physically based differentiable rendering. The seminar was highly beneficial for students, helping them understand the challenges in inverse rendering and learn about the latest advancements in noise reduction techniques.
Our PhD student Woojae Kim presented his work titled “Protecting Copyrights of NeRF Models via Adversarial Attack” at the CV4Metaverse 2024 Workshop, held during ECCV 2024. This research explores adversarial attack techniques for safeguarding the copyrights of Neural Radiance Field (NeRF) models, offering valuable insights into model protection within the 3D field.
Our lab alumni, Woobin Lim, and PhD candidate, Joomin Lee, presented their paper titled “Regularizing Dynamic Radiance Fields with Kinematic Fields” at ECCV 2024, held from September 29 to October 4, 2024. This study introduces a method for reconstructing dynamic radiance fields from monocular videos by integrating kinematics, which captures motion through quantities like velocity and acceleration. Their approach outperforms state-of-the-art methods by accurately capturing physical motion patterns in challenging real-world videos.
Professor Yoon and his Ph.D. students Woojae Kim, Jumin Lee, Jinhwan Seo along with alumnus Woobin Lim attended the ECCV 2024 conference held in Milan, Italy, from September 29th to October 4th, 2024. The team enjoyed a wonderful time walking together, catching up on recent updates, and exchanging ideas on their latest research. It was a valuable opportunity to reconnect and discuss future directions in the field.
Professor Yoon and his M.S. students attended the KAIA2024 conference in Busan from August 15th to 17th, 2024. They presented their research papers and explored the latest advancements in artificial intelligence.
Seokryun Choi presented his paper, “Event-based Trajectory Estimation of a Ball,” which proposes synthesizing event data in Isaac Gym by emulating the mechanism of event cameras.
Taeyeon Kim presented her paper, “Articulated Motion Retargeting with 4D Gaussian Splatting,” which addresses the limitations of motion retargeting between reconstructed objects in a template-free domain.
The conference offered valuable opportunities that significantly enriched their academic experience.
Our lab alumnus, Prof. Bochang Moon, participated in SIGGRAPH 2024, held in Denver from July 28 to August 1, and presented his research titled “Target-Aware Image Denoising for Inverse Monte Carlo Rendering.” This study addresses the noise issue that arises when inferring scene parameters through physically based differentiable rendering by developing a target-aware image denoiser. The research points out that using conventional image denoisers can lead to undesirable local minima due to denoising bias and proposes a new denoiser that incorporates target image information to overcome this limitation. By determining denoising weights through linear regression based on target images, this method enables more robust scene parameter inference in inverse rendering optimization.
Chanmi Lee presented a paper at the KCC2024 Conference in the Artificial Intelligence Applications section, held from June 26th to 28th, 2024. Her presentation focused on the research topic “Adversarial Attack on Visuomotor Policy.” This research reveals a vulnerability in vision-based visuomotor policies, particularly those trained with Soft Actor-Critic (SAC). To address this, she proposed a method to attack the policy, analyzing the robot’s movement path to evaluate how adversarial perturbations impact the robot’s decision-making process.
Professor Yoon and his Ph.D. students, Woobin Im, Heechan Shin, and Guoyuan An, participated in the PhD Forum session at KCC2024. They presented their research and engaged in discussions with peers about their work. Additionally, they had the opportunity to dine with professionals from companies related to their research in Korea, allowing for valuable networking and in-depth conversations. This experience provided them with a meaningful opportunity to exchange ideas and deepen their understanding of their respective fields.
Professor Yoon and his Ph.D. students, Sebin Lee, Minsung Yoon, Mincheul Kim, and M.S. student Jeil Jeong, conducted a tutorial session at the KCC2024 conference. The topic of this tutorial was “Advancements in Robot Motion Generation Techniques: From Sampling-Based to Reinforcement Learning and Applications (로봇 모션 생성 기법의 발전: 샘플링 기반에서 강화 학습 및 응용까지).”
Sebin introduced sensor technology for robot environmental perception. Minsung covered reinforcement learning techniques and their applications to robotic arms. Mincheul presented techniques for generating social paths for robots considering crowds through the integration of external sensors. Jeil explained recent advances in quadrupedal robot motion planning.
Professor Yoon and some of his Ph.D. and M.S. students attended the KCC2024 conference in Jeju from June 26th to June 28th, 2024. At the conference, they participated in paper presentations, tutorials, Ph.D. forums, and top conference sessions. Additionally, we had the opportunity to have a meal and chat with people from LG Electronics’ VS Business Division. We also visited the Arte Museum and enjoyed delicious meals, spending a fun and enjoyable time with lab members.
Jumin Lee and Sebin Lee presented their recent research, “SemCity: Semantic Scene Generation with Triplane Diffusion,” at CVPR 2024 in Seattle. This study introduces SemCity, a 3D diffusion model for generating realistic outdoor scenes using a triplane representation, enabling tasks like scene inpainting and semantic completion. Their method achieves notable results on the SemanticKITTI dataset, supporting flexible object manipulation and large-scale scene generation.
On June 17th, Youngju Na presented his recent research, UFORecon, at CVPR 2024, Seattle. The proposed work addresses the problem of generalizable surface reconstruction given a limited number of multi-view images under arbitrary and unfavorably captured conditions. It introduced a novel concept called “view-combination generalizability” in the few-shot NeRF scheme and effectively addressed it with a correlation-aware volume rendering pipeline.
Professor Yoon and his Ph.D. students, Sebin Lee, Suhyeon Ha, and Jumin Lee, along with Master’s student Youngju Na, attended the CVPR 2024 conference in Seattle, USA, from June 17th to June 21st, 2024. At the conference, we had the opportunity to reconnect with our lab alumni Inkyu An, Changho Jo, and current lab member Chungsu Jang. We enjoyed a delightful time walking together, catching up on recent events, and exchanging research ideas and thoughts.
Taegeun Yang presented a workshop paper at the IEEE IV2024 Workshop on Off-Road Autonomy, held from June 2nd to 6th, 2024. His presentation focused on the research topic “Analysis of Terrain-Aware Optimal Path Planning Methods for Stable Off-Road Navigation”. This research introduces an optimal path planning algorithm that considers terrain features to ensure stable off-road navigation, enhancing the vehicle’s ability to navigate various off-road conditions effectively and thereby improving stability.
Our lab members Yaxin, Juhyeong, and Woojung successfully defended their theses on June 6th, 2024. Yaxin presented her research thesis “Controllable Multi-Style Transfer with Diffusion Models.” Juhyeong introduced his research “SAM-based Audio-Visual Segmentation with Spatio-Temporal, Bidirectional Audio-Visual Attention.” Woojung explained his research “Towards Robustness against Domain Shift in Image Classification and Retrieval.”
Congratulations on all your hard work over the past two years!
