10 papers · 1 filter
LagerNVS: Latent Geometry for Fully Neural Real-time Novel View Synthesis
Stanislaw Szymanowicz, Minghao Chen, Jianyuan Wang +2
Recent work has shown that neural networks can perform 3D tasks such as Novel View Synthesis (NVS) without explicit 3D reconstruction. Even so, we argue that strong 3D inductive bi…
VGGT-
Jianyuan Wang, Minghao Chen, Shangzhan Zhang +7
Recent feed-forward reconstruction models, such as VGGT, have proven competitive with traditional optimization-based reconstructors while also providing geometry-aware features use…
ZID-Net: Zero-Inference Diffusion Prior Decoupling Network for Single Image Dehazing
Xinheng Li, Minghao Chen, Mengqing Wu +2
Single image dehazing is often constrained by a trade-off between restoration quality and computational efficiency. While efficient, CNN networks struggle to learn robust priors fo…
SceneScribe-1M: A Large-Scale Video Dataset with Comprehensive Geometric and Semantic Annotations
Yunnan Wang, Kecheng Zheng, Jianyuan Wang +8
The convergence of 3D geometric perception and video synthesis has created an unprecedented demand for large-scale video data that is rich in both semantic and spatio-temporal info…
WorldGen: From Text to Traversable and Interactive 3D Worlds
Dilin Wang, Hyunyoung Jung, Tom Monnier +22
We introduce WorldGen, a system that enables the automatic creation of large-scale, interactive 3D worlds directly from text prompts. Our approach transforms natural language descr…
TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility
Saman Motamed, Minghao Chen, Luc Van Gool +1
Despite impressive visual fidelity, modern video generative models frequently produce sequences that violate intuitive physical laws, such as objects floating, teleporting, or morp…