5 papers
HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos
Jeongeun Park, Janghyeok Han, Geonung Kim +4
Video outpainting generates plausible visual content beyond the original spatial extent of a video, playing a key role in adapting videos to diverse display formats. To support suc…
DynaVid: Learning to Generate Highly Dynamic Videos using Synthetic Motion Data
Wonjoon Jin, Jiyun Won, Janghyeok Han +4
Despite recent progress, video diffusion models still struggle to synthesize realistic videos involving highly dynamic motions or requiring fine-grained motion controllability. A c…
VideoFrom3D: 3D Scene Video Generation via Complementary Image and Video Diffusion Models
Geonung Kim, Janghyeok Han, Sunghyun Cho
In this paper, we propose VideoFrom3D, a novel framework for synthesizing high-quality 3D scene videos from coarse geometry, a camera trajectory, and a reference image. Our approac…
DC-VSR: Spatially and Temporally Consistent Video Super-Resolution with Video Diffusion Prior
Janghyeok Han, Gyujin Sim, Geonung Kim +4
Video super-resolution (VSR) aims to reconstruct a high-resolution (HR) video from a low-resolution (LR) counterpart. Achieving successful VSR requires producing realistic HR detai…
Exploiting Deblurring Networks for Radiance Fields
Haeyun Choi, Heemin Yang, Janghyeok Han +1
In this paper, we propose DeepDeblurRF, a novel radiance field deblurring approach that can synthesize high-quality novel views from blurred training views with significantly reduc…