6 papers
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…
Learning Zero-Shot Subject-Driven Video Generation Using 1% Compute
Daneul Kim, Jingxu Zhang, Wonjoon Jin +4
Subject-driven video generation (SDV-Gen) aims to produce videos of a specific subject by adapting a pretrained video model, enabling personalized and application-driven content cr…
FloVD: Optical Flow Meets Video Diffusion Model for Enhanced Camera-Controlled Video Synthesis
Wonjoon Jin, Qi Dai, Chong Luo +2
We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. Th…
Generalizable Novel-View Synthesis using a Stereo Camera
Haechan Lee, Wonjoon Jin, Seung-Hwan Baek +1
In this paper, we propose the first generalizable view synthesis approach that specifically targets multi-view stereo-camera images. Since recent stereo matching has demonstrated a…
SideGAN: 3D-Aware Generative Model for Improved Side-View Image Synthesis
Kyungmin Jo, Wonjoon Jin, Jaegul Choo +2
While recent 3D-aware generative models have shown photo-realistic image synthesis with multi-view consistency, the synthesized image quality degrades depending on the camera pose…
Dr.3D: Adapting 3D GANs to Artistic Drawings
Wonjoon Jin, Nuri Ryu, Geonung Kim +2
While 3D GANs have recently demonstrated the high-quality synthesis of multi-view consistent images and 3D shapes, they are mainly restricted to photo-realistic human portraits. Th…