DreamDissector: Learning Disentangled Text-to-3D Generation from 2D Diffusion Priors
This addresses a practical need in text-to-3D generation for creative applications by enabling object-level control, though it appears incremental as it builds on prior diffusion and NeRF techniques.
The paper tackled the problem of generating multiple independent 3D objects with plausible interactions from text, which existing methods struggle with, and proposed DreamDissector, a method that produces independent textured meshes from a multi-object NeRF input, validated by experimental results.
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.