12 citations · 14 across the 7 of their papers we have counts for
10 papers
Beyond the Verdict: Evidence-Aligned Evaluation of Visual Prompt-Injection Guardrails
Suyoung Lee, Myungsub Choi
Verdict-only evaluation does not reveal whether a vision-language model (VLM) used the visual evidence that should support its decision. We study this problem in web-agent guardrai…
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…
StarryGazer: Leveraging Monocular Depth Estimation Models for Domain-Agnostic Single Depth Image Completion
Sangmin Hong, Suyoung Lee, Kyoung Mu Lee
The problem of depth completion involves predicting a dense depth image from a single sparse depth map and an RGB image. Unsupervised depth completion methods have been proposed fo…
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…
ODGS: 3D Scene Reconstruction from Omnidirectional Images with 3D Gaussian Splattings
Suyoung Lee, Jaeyoung Chung, Jaeyoo Huh +1
Omnidirectional (or 360-degree) images are increasingly being used for 3D applications since they allow the rendering of an entire scene with a single image. Existing works based o…
LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes
Jaeyoung Chung, Suyoung Lee, Hyeongjin Nam +2
With the widespread usage of VR devices and contents, demands for 3D scene generation techniques become more popular. Existing 3D scene generation models, however, limit the target…
NTIRE 2021 Challenge on Video Super-Resolution
Sanghyun Son, Suyoung Lee, Seungjun Nah +2
Super-Resolution (SR) is a fundamental computer vision task that aims to obtain a high-resolution clean image from the given low-resolution counterpart. This paper reviews the NTIR…
NTIRE 2021 Challenge on Image Deblurring
Seungjun Nah, Sanghyun Son, Suyoung Lee +2
Motion blur is a common photography artifact in dynamic environments that typically comes jointly with the other types of degradation. This paper reviews the NTIRE 2021 Challenge o…
DynaVSR: Dynamic Adaptive Blind Video Super-Resolution
Suyoung Lee, Myungsub Choi, Kyoung Mu Lee
Most conventional supervised super-resolution (SR) algorithms assume that low-resolution (LR) data is obtained by downscaling high-resolution (HR) data with a fixed known kernel, b…