Sketch2NeRF: Multi-view Sketch-guided Text-to-3D Generation

TL;DR

Sketch2NeRF introduces a multi-view sketch-guided framework for text-to-3D generation, enabling fine-grained control and high-fidelity 3D content synthesis by leveraging pretrained 2D diffusion models.

Contribution

It presents a novel synchronized generation and reconstruction method to incorporate sketch control into neural radiance field-based 3D generation.

Findings

Achieves state-of-the-art sketch similarity and text alignment.

Synthesizes 3D content with fine-grained sketch control.

Produces high-fidelity, multi-view consistent 3D models.

Abstract

Recently, text-to-3D approaches have achieved high-fidelity 3D content generation using text description. However, the generated objects are stochastic and lack fine-grained control. Sketches provide a cheap approach to introduce such fine-grained control. Nevertheless, it is challenging to achieve flexible control from these sketches due to their abstraction and ambiguity. In this paper, we present a multi-view sketch-guided text-to-3D generation framework (namely, Sketch2NeRF) to add sketch control to 3D generation. Specifically, our method leverages pretrained 2D diffusion models (e.g., Stable Diffusion and ControlNet) to supervise the optimization of a 3D scene represented by a neural radiance field (NeRF). We propose a novel synchronized generation and reconstruction method to effectively optimize the NeRF. In the experiments, we collected two kinds of multi-view sketch datasets to evaluate the proposed method. We demonstrate that our method can synthesize 3D consistent contents with fine-grained sketch control while being high-fidelity to text prompts. Extensive results show that our method achieves state-of-the-art performance in terms of sketch similarity and text alignment.