DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors

TL;DR

DreamDissector introduces a novel method for generating multiple independent and interacting objects in 3D scenes from text prompts, advancing the realism and controllability of text-to-3D generation.

Contribution

It proposes Neural Category Field and Category Score Distillation Sampling to disentangle and generate multi-object 3D scenes, addressing limitations of existing methods.

Findings

Successfully generates multi-object 3D scenes with interactions

Enables object-level control in 3D synthesis

Outperforms existing methods in realism and diversity

Abstract

Text-to-3D generation has recently seen significant progress. To enhance its practicality in real-world applications, it is crucial to generate multiple independent objects with interactions, similar to layer-compositing in 2D image editing. However, existing text-to-3D methods struggle with this task, as they are designed to generate either non-independent objects or independent objects lacking spatially plausible interactions. Addressing this, we propose DreamDissector, a text-to-3D method capable of generating multiple independent objects with interactions. DreamDissector accepts a multi-object text-to-3D NeRF as input and produces independent textured meshes. To achieve this, we introduce the Neural Category Field (NeCF) for disentangling the input NeRF. Additionally, we present the Category Score Distillation Sampling (CSDS), facilitated by a Deep Concept Mining (DCM) module, to tackle the concept gap issue in diffusion models. By leveraging NeCF and CSDS, we can effectively derive sub-NeRFs from the original scene. Further refinement enhances geometry and texture. Our experimental results validate the effectiveness of DreamDissector, providing users with novel means to control 3D synthesis at the object level and potentially opening avenues for various creative applications in the future.