Reconstruction of a 3D wireframe from a single line drawing via generative depth estimation

arXiv cs.CV / 4/16/2026

📰 NewsSignals & Early TrendsIdeas & Deep AnalysisModels & Research

共有:

Key Points

The paper tackles the problem of reconstructing 3D wireframes from a single 2D freehand line drawing, aiming to bridge human sketching and digital 3D modeling.
Instead of brittle symbolic logic or rigid CAD-style parametric modeling, it formulates reconstruction as conditional dense depth estimation.
The approach uses a Latent Diffusion Model (LDM) with ControlNet-style conditioning to resolve ambiguities caused by orthographic projections.
To enable an iterative “sketch-reconstruct-sketch” workflow, it introduces a graph-based BFS masking strategy that simulates partial depth cues from incomplete sketches.
The method is trained and evaluated on a large dataset (over one million image-depth pairs) derived from the ABC Dataset and reports robust results across shape complexities.

Abstract

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.