20 papers
Glob3R: Global Structure-from-Motion with 3D Foundation Models
Junyuan Deng, Heng Li, Kejie Qiu +7
Recent 3D geometric foundation models, such as VGGT, provide robust feed-forward 3D reconstruction by directly predicting camera poses and 3D scene points from input images. Howeve…
Large Depth Completion Model from Sparse Observations
Zhu Yu, Zhengyi Zhao, Runmin Zhang +7
This work presents the Large Depth Completion Model (LDCM), a simple, effective, and robust framework for single-view metric depth estimation with sparse observations. Without rely…
LHM++: An Efficient Large Human Reconstruction Model for Pose-free Images to 3D
Lingteng Qiu, Peihao Li, Heyuan Li +9
Reconstructing animatable 3D humans from casually captured images of articulated subjects without camera or pose information is highly practical but remains challenging due to view…
Head-wise Adaptive Rotary Positional Encoding for Fine-Grained Image Generation
Jiaye Li, Baoyou Chen, Hui Li +3
Transformers rely on explicit positional encoding to model structure in data. While Rotary Position Embedding (RoPE) excels in 1D domains, its application to image generation revea…
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…