CVMMSep 11, 2024

DreamMesh: Jointly Manipulating and Texturing Triangle Meshes for Text-to-3D Generation

arXiv:2409.07454v118 citationsh-index: 58
Originality Incremental advance
AI Analysis

This work solves the problem of producing explicit, textured 3D meshes from text for applications in 3D modeling and content creation, representing an incremental improvement over existing text-to-3D methods.

The paper tackles the problem of generating high-fidelity 3D models from text by addressing issues like noisy surfaces and cross-view inconsistency in implicit representations like NeRF, resulting in DreamMesh, which significantly outperforms state-of-the-art methods in generating 3D content with richer textual details and enhanced geometry.

Learning radiance fields (NeRF) with powerful 2D diffusion models has garnered popularity for text-to-3D generation. Nevertheless, the implicit 3D representations of NeRF lack explicit modeling of meshes and textures over surfaces, and such surface-undefined way may suffer from the issues, e.g., noisy surfaces with ambiguous texture details or cross-view inconsistency. To alleviate this, we present DreamMesh, a novel text-to-3D architecture that pivots on well-defined surfaces (triangle meshes) to generate high-fidelity explicit 3D model. Technically, DreamMesh capitalizes on a distinctive coarse-to-fine scheme. In the coarse stage, the mesh is first deformed by text-guided Jacobians and then DreamMesh textures the mesh with an interlaced use of 2D diffusion models in a tuning free manner from multiple viewpoints. In the fine stage, DreamMesh jointly manipulates the mesh and refines the texture map, leading to high-quality triangle meshes with high-fidelity textured materials. Extensive experiments demonstrate that DreamMesh significantly outperforms state-of-the-art text-to-3D methods in faithfully generating 3D content with richer textual details and enhanced geometry. Our project page is available at https://dreammesh.github.io.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes