8 papers
Marrying Optimal Transport and ODEs for Unified Continuous-Time 4D Reconstruction and Tracking
Liying Yang, Hao Mo, Jialun Liu +7
Existing unified 4D reconstruction and point tracking approaches typically rely on heuristic interpolations or just predict at integer timestamps, lacking kinematic coherence and f…
SIFT: Self-Imagination Fine-Tuning for Physically Plausible Motion in Video Diffusion Models
Ruoyu Wang, Jialun Liu, Huayang Huang +5
Recent advances in video diffusion models have greatly improved visual fidelity, yet their generated motions often violate physical plausibility. We observe a common kinematic fail…
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Xiao Cao, Yansong Qu, Xiangzhen +8
Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, existing methods struggle whe…
LiftAvatar: Kinematic-Space Completion for Expression-Controlled 3D Gaussian Avatar Animation
Hualiang Wei, Shunran Jia, Jialun Liu +1
We present LiftAvatar, a new paradigm that completes sparse monocular observations in kinematic space (e.g., facial expressions and head pose) and uses the completed signals to dri…
Geometry-as-context: Modulating Explicit 3D in Scene-consistent Video Generation to Geometry Context
JiaKui Hu, Jialun Liu, Liying Yang +7
Scene-consistent video generation aims to create videos that explore 3D scenes based on a camera trajectory. Previous methods rely on video generation models with external memory f…
Tele-Omni: a Unified Multimodal Framework for Video Generation and Editing
Jialun Liu, Tian Li, Xiao Cao +20
Recent advances in diffusion-based video generation have substantially improved visual fidelity and temporal coherence. However, most existing approaches remain task-specific and r…
Spatial-Temporal State Propagation Autoregressive Model for 4D Object Generation
Liying Yang, Jialun Liu, Jiakui Hu +5
Generating high-quality 4D objects with spatial-temporal consistency is still formidable. Existing diffusion-based methods often struggle with spatial-temporal inconsistency, as th…
CtrlVDiff: Controllable Video Generation via Unified Multimodal Video Diffusion
Dianbing Xi, Jiepeng Wang, Yuanzhi Liang +8
We tackle the dual challenges of video understanding and controllable video generation within a unified diffusion framework. Our key insights are two-fold: geometry-only cues (e.g.…