11 papers
VGenST-Bench: A Benchmark for Spatio-Temporal Reasoning via Active Video Synthesis
Jinho Park, Youbin Kim, Hogun Park +1
Spatio-temporal reasoning is a core capability for Multimodal Large Language Models (MLLMs) operating in the real world. As such, evaluating it precisely has become an essential ch…
Group3D: MLLM-Driven Semantic Grouping for Open-Vocabulary 3D Object Detection
Youbin Kim, Jinho Park, Hogun Park +1
Open-vocabulary 3D object detection aims to localize and recognize objects beyond a fixed training taxonomy. In multi-view RGB settings, recent approaches often decouple geometry-b…
3DreamBooth: High-Fidelity 3D Subject-Driven Video Generation Model
Hyun-kyu Ko, Jihyeon Park, Younghyun Kim +2
Creating dynamic, view-consistent videos of customized subjects is highly sought after for a wide range of emerging applications, including immersive VR/AR, virtual production, and…
2Xplat: Decoupling Geometry and Appearance Modeling for Feed-Forward 3D Gaussian Splatting
Hwasik Jeong, Seungryong Lee, Gyeongjin Kang +4
Pose-free feed-forward 3D Gaussian Splatting (3DGS) has opened a new frontier for rapid 3D modeling, enabling high-quality Gaussian representations to be generated from uncalibrate…
OpenMonoGS-SLAM: Monocular Gaussian Splatting SLAM with Open-set Semantics
Jisang Yoo, Gyeongjin Kang, Hyun-kyu Ko +2
Simultaneous Localization and Mapping (SLAM) is a foundational component in robotics, AR/VR, and autonomous systems. With the rising focus on spatial AI in recent years, combining…
Multi-view Pyramid Transformer: Look Coarser to See Broader
Gyeongjin Kang, Seungkwon Yang, Seungtae Nam +3
We propose Multi-view Pyramid Transformer (MVP), a scalable multi-view transformer architecture that directly reconstructs large 3D scenes from tens to hundreds of images in a sing…
Gather-Scatter Mamba: Accelerating Propagation with Efficient State Space Model
Hyun-kyu Ko, Youbin Kim, Jihyeon Park +5
State Space Models (SSMs)-most notably RNNs-have historically played a central role in sequential modeling. Although attention mechanisms such as Transformers have since dominated…
DiffuseSlide: Training-Free High Frame Rate Video Generation Diffusion
Geunmin Hwang, Hyun-kyu Ko, Younghyun Kim +2
Recent advancements in diffusion models have revolutionized video generation, enabling the creation of high-quality, temporally consistent videos. However, generating high frame-ra…
CompMarkGS: Robust Watermarking for Compressed 3D Gaussian Splatting
Sumin In, Youngdong Jang, Utae Jeong +4
As 3D Gaussian Splatting (3DGS) is increasingly adopted in various academic and commercial applications due to its high-quality and real-time rendering capabilities, the need for c…
Sequence Matters: Harnessing Video Models in 3D Super-Resolution
Hyun-kyu Ko, Dongheok Park, Youngin Park +3
3D super-resolution aims to reconstruct high-fidelity 3D models from low-resolution (LR) multi-view images. Early studies primarily focused on single-image super-resolution (SISR)…
Aberration Correcting Vision Transformers for High-Fidelity Metalens Imaging
Byeonghyeon Lee, Youbin Kim, Yongjae Jo +7
Metalens is an emerging optical system with an irreplaceable merit in that it can be manufactured in ultra-thin and compact sizes, which shows great promise in various applications…