Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper tackles the problem of reconstructing 3D wireframes from single 2D line drawings by framing it as a conditional dense depth estimation task. They implement a Latent Diffusion Model (LDM) conditioned with a ControlNet-style framework to handle ambiguities in orthographic projections. The model is trained on a large dataset of image-depth pairs and uses a graph-based BFS masking strategy for iterative refinement.
Imagine sketching in 2D and instantly getting a usable 3D model – this work brings that closer to reality by sidestepping the limitations of traditional CAD with a generative approach.
The conversion of 2D freehand sketches into 3D models remains a pivotal challenge in computer vision, bridging the gap between human creativity and digital fabrication. Traditional line drawing reconstruction relies on brittle symbolic logic, while modern approaches are constrained by rigid parametric modeling, limiting users to predefined CAD primitives. We propose a generative approach by framing reconstruction as a conditional dense depth estimation task. To achieve this, we implement a Latent Diffusion Model (LDM) with a ControlNet-style conditioning framework to resolve the inherent ambiguities of orthographic projections. To support an iterative"sketch-reconstruct-sketch"workflow, we introduce a graph-based BFS masking strategy to simulate partial depth cues. We train and evaluate our approach using a massive dataset of over one million image-depth pairs derived from the ABC Dataset. Our framework demonstrates robust performance across varying shape complexities, providing a scalable pipeline for converting sparse 2D line drawings into dense 3D representations, effectively allowing users to"draw in 3D"without the rigid constraints of traditional CAD.