6 papers
Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework
Xiao Cao, Yansong Qu, Xiangzhen +7
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…
ReImagine: Rethinking Controllable High-Quality Human Video Generation via Image-First Synthesis
Zhengwentai Sun, Keru Zheng, Chenghong Li +7
Human video generation remains challenging due to the difficulty of jointly modeling human appearance, motion, and camera viewpoint under limited multi-view data. Existing methods…
Exploring Disentangled and Controllable Human Image Synthesis: From End-to-End to Stage-by-Stage
Zhengwentai Sun, Chenghong Li, Hongjie Liao +7
Achieving fine-grained controllability in human image synthesis is a long-standing challenge in computer vision. Existing methods primarily focus on either facial synthesis or near…
Condition Matters in Full-head 3D GANs
Heyuan Li, Huimin Zhang, Yuda Qiu +10
Conditioning is crucial for stable training of full-head 3D GANs. Without any conditioning signal, the model suffers from severe mode collapse, making it impractical to training. H…
HyPlaneHead: Rethinking Tri-plane-like Representations in Full-Head Image Synthesis
Heyuan Li, Kenkun Liu, Lingteng Qiu +4
Tri-plane-like representations have been widely adopted in 3D-aware GANs for head image synthesis and other 3D object/scene modeling tasks due to their efficiency. However, queryin…
ViSA: 3D-Aware Video Shading for Real-Time Upper-Body Avatar Creation
Fan Yang, Heyuan Li, Peihao Li +9
Generating high-fidelity upper-body 3D avatars from one-shot input image remains a significant challenge. Current 3D avatar generation methods, which rely on large reconstruction m…