arXiv subjects

Bingchen Yang

Publications and source records attributed to Bingchen Yang.

4 recordsLinked to original sources

arXiv2026

TG-Diff: Coupling Discrete Topology Diffusion and Topology-conditioned Geometry Diffusions for B-Rep Generation

Boundary representation (B-rep) is the standard format for computer-aided design (CAD). This article proposes a lightweight two-stage diffusion-based B-rep generation framework, TG-Diff, that achieves efficient, high-quality B-rep generation by decoupling topology and geometric modeling. In contrast to previous work that generates topology as a collection of vertices, edges, and surfaces together with their relationships, TG-Diff represents topology only as a collection of surfaces and their adjacency relationships. This surface-centric representation inherently alleviates the geometric and topological inconsistencies between separately generated surfaces, edges, and vertices, simplifying the generation process. Based on the surface-centric representation, we develop two independent diffusion models that generate surface adjacency relationships and surface latents, respectively. By using topology as guidance, the surface generation process becomes more stable, leading to stronger structural completeness in the generated B-rep models. The topology diffusion model adopts a Discrete Diffusion Model (D3PM) for efficient binary sampling, avoiding the slow inference of autoregressive methods. Surface latent generation employs a conditional latent diffusion model with a lightweight DiT architecture, where surface adjacency guides geometry generation while reducing computational cost. Finally, edges and vertices are derived from the decoded adjacent surfaces via post-processing to form a final watertight B-rep. Despite its compact computational footprint (82.18M parameters and 2.2 GFLOPs), TG-Diff excels in the validity metric while achieving superior performance on all COV, MMD, and JSD metrics across the DeepCAD and ABC datasets.

cs.CG↗

arXiv2025

CADCrafter: Generating Computer-Aided Design Models from Unconstrained Images

Creating CAD digital twins from the physical world is crucial for manufacturing, design, and simulation. However, current methods typically rely on costly 3D scanning with labor-intensive post-processing. To provide a user-friendly design process, we explore the problem of reverse engineering from unconstrained real-world CAD images that can be easily captured by users of all experiences. However, the scarcity of real-world CAD data poses challenges in directly training such models. To tackle these challenges, we propose CADCrafter, an image-to-parametric CAD model generation framework that trains solely on synthetic textureless CAD data while testing on real-world images. To bridge the significant representation disparity between images and parametric CAD models, we introduce a geometry encoder to accurately capture diverse geometric features. Moreover, the texture-invariant properties of the geometric features can also facilitate the generalization to real-world scenarios. Since compiling CAD parameter sequences into explicit CAD models is a non-differentiable process, the network training inherently lacks explicit geometric supervision. To impose geometric validity constraints, we employ direct preference optimization (DPO) to fine-tune our model with the automatic code checker feedback on CAD sequence quality. Furthermore, we collected a real-world dataset, comprised of multi-view images and corresponding CAD command sequence pairs, to evaluate our method. Experimental results demonstrate that our approach can robustly handle real unconstrained CAD images, and even generalize to unseen general objects.

cs.CV↗

arXiv2025

HierRelTriple: Guiding Indoor Layout Generation with Hierarchical Relationship Triplet Losses

We present a hierarchical triplet-based indoor relationship learning method, coined HierRelTriple, with a focus on spatial relationship learning. Existing approaches often depend on manually defined spatial rules or simplified pairwise representations, which fail to capture complex, multi-object relationships found in real scenarios and lead to overcrowded or physically implausible arrangements. We introduce HierRelTriple, a hierarchical relational triplets modeling framework that first partitions functional regions and then automatically extracts three levels of spatial relationships: object-to-region (O2R), object-to-object (O2O), and corner-to-corner (C2C). By representing these relationships as geometric triplets and employing approaches based on Delaunay Triangulation to establish spatial priors, we derive IoU loss between denoised and ground truth triplets and integrate them seamlessly into the diffusion denoising process. The introduction of the joint formulation of inter-object distances, angular orientations, and spatial relationships enhances the physical realism of the generated scenes. Extensive experiments on unconditional layout synthesis, floorplan-conditioned layout generation, and scene rearrangement demonstrate that HierRelTriple improves spatial-relation metrics by over 15% and substantially reduces collisions and boundary violations compared to state-of-the-art methods.

cs.CV↗

arXiv2024

PS-CAD: Local Geometry Guidance via Prompting and Selection for CAD Reconstruction

Reverse engineering CAD models from raw geometry is a classic but challenging research problem. In particular, reconstructing the CAD modeling sequence from point clouds provides great interpretability and convenience for editing. To improve upon this problem, we introduce geometric guidance into the reconstruction network. Our proposed model, PS-CAD, reconstructs the CAD modeling sequence one step at a time. At each step, we provide two forms of geometric guidance. First, we provide the geometry of surfaces where the current reconstruction differs from the complete model as a point cloud. This helps the framework to focus on regions that still need work. Second, we use geometric analysis to extract a set of planar prompts, that correspond to candidate surfaces where a CAD extrusion step could be started. Our framework has three major components. Geometric guidance computation extracts the two types of geometric guidance. Single-step reconstruction computes a single candidate CAD modeling step for each provided prompt. Single-step selection selects among the candidate CAD modeling steps. The process continues until the reconstruction is completed. Our quantitative results show a significant improvement across all metrics. For example, on the dataset DeepCAD, PS-CAD improves upon the best published SOTA method by reducing the geometry errors (CD and HD) by 10%, and the structural error (ECD metric) by about 15%.

cs.CV↗