4 papers
From Feed-Forward to Flow: Unifying Reconstruction and Generation Is Easier Than You Think
Haoru Wang, Qianfan Shen, Kai Ye +2
Reconstruct where the images provide evidence, and generate where they do not: recent success of spatial world models such as Atlas (World Labs Team, 2026) highlights the value of…
Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling
Minghan Qin, Yuang Wang, Xiuyu Yang +6
Composable scene modeling aims to recover a real indoor scene as complete, editable object assets arranged as observed, giving robot simulation and embodied AI a simulation-ready r…
The Less You Depend, The More You Learn: Synthesizing Novel Views from Sparse, Unposed Images with Minimal 3D Knowledge
Haoru Wang, Kai Ye, Minghan Qin +3
Recent advances in feed-forward Novel View Synthesis (NVS) have led to a divergence between two design philosophies: bias-driven methods, which rely on explicit 3D knowledge, such…
GeoSplatting: Towards Geometry Guided Gaussian Splatting for Physically-based Inverse Rendering
Kai Ye, Chong Gao, Guanbin Li +2
Recent 3D Gaussian Splatting (3DGS) representations have demonstrated remarkable performance in novel view synthesis; further, material-lighting disentanglement on 3DGS warrants re…