7 papers
ConCAD: Constraint-Aware Image-to-CAD Generation with Dual-Granularity Rewards
Chenxi Zhai, Xi Cheng, Hang Cheng +5
Image-to-CAD generation seeks executable parametric programs that recover both the geometry and design intent of a reference object. Existing systems are commonly evaluated by vali…
DIP-CAD: A Design-Intent-Preserving Agent Harness for Parametric CAD Modeling
Xi Cheng, Chenxi Zhai, Hang Cheng +3
Parametric CAD modeling requires not only matching the target shape, but also preserving design intent under parameter edits. However, most existing methods focus on improving stat…
Refine Then Fusion: Training-Free 3D Point Cloud Adaptation with Priority Refinement and Multi-Modal Knowledge Fusion
Hang Cheng, Yan Chen, Mingyu Fan +1
Recent pre-trained foundation models provide rich multi-modal priors for downstream 3D vision tasks. However, the effectiveness of these representations in few-shot scenarios is li…
Multi-View Hierarchical Graph Neural Network for Sketch-Based 3D Shape Retrieval
Hang Cheng, Muyan He, Mingyu Fan +3
Sketch-based 3D shape retrieval (SBSR) aims to retrieve 3D shapes that are consistent with the category of the input hand-drawn sketch. The core challenge of this task lies in two…
TaPD: Temporal-adaptive Progressive Distillation for Observation-Adaptive Trajectory Forecasting in Autonomous Driving
Mingyu Fan, Yi Liu, Hao Zhou +3
Trajectory prediction is essential for autonomous driving, enabling vehicles to anticipate the motion of surrounding agents to support safe planning. However, most existing predict…
Manifold-Aware Point Cloud Completion via Geodesic-Attentive Hierarchical Feature Learning
Jianan Sun, Dongzhihan Wang, Mingyu Fan
Point cloud completion seeks to recover geometrically consistent shapes from partial or sparse 3D observations. Although recent methods have achieved reasonable global shape recons…
Memory-Guided Point Cloud Completion for Dental Reconstruction
Jianan Sun, Yukang Huang, Dongzhihan Wang +1
Partial dental point clouds often suffer from large missing regions caused by occlusion and limited scanning views, which bias encoder-only global features and force decoders to ha…