11 papers
MAGE: View-guided Point Cloud Completion with Efficient Modality Alignment and Adaptive Geometry Enhancement
Weize Quan, Zhengwei Wu, Kai Wang +1
View-based point cloud completion aims to recover a complete 3D shape from a partial point cloud, guided by a single-view image. However, existing approaches often suffer from limi…
COMPASS: Grounding Composition-Intent Guidance in Unified Multimodal Models
Ziqi Zhou, Weize Quan, Mining Tan +6
Composition is a high-level visual intent that governs where subjects are placed and how a scene is organized, yet current unified multimodal models remain unreliable at fine-grain…
CasLayout: Cascaded 3D Layout Diffusion for Indoor Scene Synthesis with Implicit Relation Modeling
Yingrui Wu, Youkang Kong, Mingyang Zhao +3
Synthesizing realistic 3D indoor scenes remains challenging due to data scarcity and the difficulty of simultaneously enforcing global architectural constraints and local semantic…
RefReward-SR: LR-Conditioned Reward Modeling for Preference-Aligned Super-Resolution
Yushuai Song, Weize Quan, Weining Wang +8
Recent advances in generative super-resolution (SR) have greatly improved visual realism, yet existing evaluation and optimization frameworks remain misaligned with human perceptio…
FACE: A Face-based Autoregressive Representation for High-Fidelity and Efficient Mesh Generation
Hanxiao Wang, Yuan-Chen Guo, Ying-Tian Liu +6
Autoregressive models for 3D mesh generation suffer from a fundamental limitation: they flatten meshes into long vertex-coordinate sequences. This results in prohibitive computatio…
BrepGPT: Autoregressive B-rep Generation with Voronoi Half-Patch
Pu Li, Wenhao Zhang, Weize Quan +3
Boundary representation (B-rep) is the de facto standard for CAD model representation in modern industrial design. The intricate coupling between geometric and topological elements…