6 papers
Map2World: Segment Map Conditioned Text to 3D World Generation
Jaeyoung Chung, Suyoung Lee, Jianfeng Xiang +2
3D world generation is essential for applications such as immersive content creation or autonomous driving simulation. Recent advances in 3D world generation have shown promising r…
InpaintSLat: Inpainting Structured 3D Latents via Initial Noise Optimization
Jaeyoung Chung, Suyoung Lee, Kyoung Mu Lee
We present a training-free approach for controllable 3D inpainting based on initial noise optimization. In the structured 3D latent diffusion framework, we observe that the underly…
Generative Phomosaic with Structure-Aligned and Personalized Diffusion
Jaeyoung Chung, Hyunjin Son, Kyoung Mu Lee
We present the first generative approach to photomosaic creation. Traditional photomosaic methods rely on a large number of tile images and color-based matching, which limits both…
MARS2 2025 Challenge on Multimodal Reasoning: Datasets, Methods, Results, Discussion, and Outlook
Peng Xu, Shengwu Xiong, Jiajun Zhang +125
This paper reviews the MARS2 2025 Challenge on Multimodal Reasoning. We aim to bring together different approaches in multimodal machine learning and LLMs via a large benchmark. We…
OmniSplat: Taming Feed-Forward 3D Gaussian Splatting for Omnidirectional Images with Editable Capabilities
Suyoung Lee, Jaeyoung Chung, Kihoon Kim +4
Feed-forward 3D Gaussian splatting (3DGS) models have gained significant popularity due to their ability to generate scenes immediately without needing per-scene optimization. Alth…
DeClotH: Decomposable 3D Cloth and Human Body Reconstruction from a Single Image
Hyeongjin Nam, Donghwan Kim, Jeongtaek Oh +1
Most existing methods of 3D clothed human reconstruction from a single image treat the clothed human as a single object without distinguishing between cloth and human body. In this…