6 papers
PoseAdapter: Dual-Stream 2.5D Controllable Image Generation for Complex Multi-Object Scenes
Yufeng Chi, Huimin Ma, Fan Gao +3
While Text-to-Image (T2I) diffusion models have achieved remarkable success, precise spatial and orientational control in multi-object scenes remains a persistent challenge. Existi…
Decoupling Cross-Modality Manifold Discrepancy: Leveraging Visible Diffusion Priors for Infrared Super-Resolution
Yunpeng Hua, Hongwei Yu, Jiawei Li +3
Infrared image super-resolution (IISR) mitigates the limitations imposed by low spatial resolution. Existing methods have recognized that IISR should preserve consistency in global…
Unposed-to-3D: Learning Simulation-Ready Vehicles from Real-World Images
Hongyuan Liu, Bochao Zou, Qiankun Liu +10
Creating realistic and simulation-ready 3D assets is crucial for autonomous driving research and virtual environment construction. However, existing 3D vehicle generation methods a…
XYZCylinder: Towards Compatible Feed-Forward 3D Gaussian Splatting for Driving Scenes via Unified Cylinder Lifting Method
Haochen Yu, Qiankun Liu, Hongyuan Liu +4
Feed-forward paradigms for 3D reconstruction have become a focus of recent research, which learn implicit, fixed view transformations to generate a single scene representation. How…
MVSMamba: Multi-View Stereo with State Space Model
Jianfei Jiang, Qiankun Liu, Hongyuan Liu +4
Robust feature representations are essential for learning-based Multi-View Stereo (MVS), which relies on accurate feature matching. Recent MVS methods leverage Transformers to capt…
DisCo3D: Distilling Multi-View Consistency for 3D Scene Editing
Yufeng Chi, Huimin Ma, Kafeng Wang +1
While diffusion models have demonstrated remarkable progress in 2D image generation and editing, extending these capabilities to 3D editing remains challenging, particularly in mai…