5 papers
ControlFlow3D: Distilling Multi-View Knowledge into Latent Flow Matching for Point Cloud Upsampling
Yuang Liu, Zhi Zuo, Zhengkai Zhao +4
Point cloud upsampling is essential for 3D applications but remains challenging due to sparse, under-constrained observations. Multi-view images can resolve geometric ambiguity, bu…
MultiCompose: Multi-Concept Personalized Composition with Per-Subject Attribute Binding
Ruirui Zhang, Zhengkai Zhao, Pan Gao
Text-to-image diffusion models enable personalization of specific visual concepts from a small number of reference images. However, generating a single image that contains multiple…
Frequency-Aware Dual-Stream Learning for Balanced Realism and Fidelity in Electron Microscopy Imaging
Longmi Gao, Zhengkai Zhao, Pan Gao +1
Electron microscopy enables nanoscale cellular visualization but faces a trade-off between imaging resolution and acquisition speed. Existing learning-based methods rely on single-…
GrainGS: Gradient-Decoupled Gaussian Splatting for Efficient Dynamic Novel View Synthesis
Jiahao He, Yihua Shao, Zhengkai Zhao +6
Dynamic scene reconstruction with 3D Gaussian Splatting requires a balance between fine-grained motion modeling, structural stability, and compact representation. Existing per-prim…
Simba: Towards High-Fidelity and Geometrically-Consistent Point Cloud Completion via Transformation Diffusion
Lirui Zhang, Zhengkai Zhao, Zhi Zuo +2
Point cloud completion is a fundamental task in 3D vision. A persistent challenge in this field is simultaneously preserving fine-grained details present in the input while ensurin…