MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR

• URL: http://arxiv.org/abs/2308.09278v1
• Date: Fri, 18 Aug 2023 03:40:38 GMT
• Title: MATLABER: Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR
• Authors: Xudong Xu, Zhaoyang Lyu, Xingang Pan, Bo Dai
• Abstract summary: We propose Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR (textbfMATLABER) We train this auto-encoder with large-scale real-world BRDF collections and ensure the smoothness of its latent space. Our approach demonstrates the superiority over existing ones in generating realistic and coherent object materials.
• Score: 29.96046140529936
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Based on powerful text-to-image diffusion models, text-to-3D generation has made significant progress in generating compelling geometry and appearance. However, existing methods still struggle to recover high-fidelity object materials, either only considering Lambertian reflectance, or failing to disentangle BRDF materials from the environment lights. In this work, we propose Material-Aware Text-to-3D via LAtent BRDF auto-EncodeR (\textbf{MATLABER}) that leverages a novel latent BRDF auto-encoder for material generation. We train this auto-encoder with large-scale real-world BRDF collections and ensure the smoothness of its latent space, which implicitly acts as a natural distribution of materials. During appearance modeling in text-to-3D generation, the latent BRDF embeddings, rather than BRDF parameters, are predicted via a material network. Through exhaustive experiments, our approach demonstrates the superiority over existing ones in generating realistic and coherent object materials. Moreover, high-quality materials naturally enable multiple downstream tasks such as relighting and material editing. Code and model will be publicly available at \url{https://sheldontsui.github.io/projects/Matlaber}.

Related papers

• MatCLIP: Light- and Shape-Insensitive Assignment of PBR Material Models [42.42328559042189]
  MatCLIP is a novel method that extracts shape- and lighting-insensitive descriptors of PBR materials to assign plausible textures to 3D objects based on images. By extending an Alpha-CLIP-based model on material renderings across diverse shapes and lighting, our approach generates descriptors that bridge the domains of PBR representations with photographs or renderings. MatCLIP achieves a top-1 classification accuracy of 76.6%, outperforming state-of-the-art methods such as PhotoShape and MatAtlas.
  arXiv  Detail & Related papers  (2025-01-27T12:08:52Z)
• TexGaussian: Generating High-quality PBR Material via Octree-based 3D Gaussian Splatting [48.97819552366636]
  This paper presents TexGaussian, a novel method that uses octant-aligned 3D Gaussian Splatting for rapid PBR material generation. Our method synthesizes more visually pleasing PBR materials and runs faster than previous methods in both unconditional and text-conditional scenarios.
  arXiv  Detail & Related papers  (2024-11-29T12:19:39Z)
• Boosting 3D Object Generation through PBR Materials [32.732511476490316]
  We propose a novel approach to boost the quality of generated 3D objects from the perspective of Physics-Based Rendering (PBR) materials. For albedo and bump maps, we leverage Stable Diffusion fine-tuned on synthetic data to extract these values. In terms of roughness and metalness maps, we adopt a semi-automatic process to provide room for interactive adjustment.
  arXiv  Detail & Related papers  (2024-11-25T04:20:52Z)
• Meta 3D AssetGen: Text-to-Mesh Generation with High-Quality Geometry, Texture, and PBR Materials [58.178540282148475]
  AssetGen is a significant advancement in text-to-3D generation. It produces faithful, high-quality meshes with texture and material control.
  arXiv  Detail & Related papers  (2024-07-02T17:21:47Z)
• Make-it-Real: Unleashing Large Multimodal Model for Painting 3D Objects with Realistic Materials [108.59709545364395]
  GPT-4V can effectively recognize and describe materials, allowing the construction of a detailed material library. The correctly matched materials are then meticulously applied as reference for the new SVBRDF material generation. Make-it-Real offers a streamlined integration into the 3D content creation workflow.
  arXiv  Detail & Related papers  (2024-04-25T17:59:58Z)
• DreamPBR: Text-driven Generation of High-resolution SVBRDF with Multi-modal Guidance [9.214785726215942]
  We propose a novel diffusion-based generative framework designed to create spatially-varying appearance properties guided by text and multi-modal controls. Key to achieving diverse and high-quality PBR material generation lies in integrating the capabilities of recent large-scale vision-language models trained on billions of text-image pairs. We demonstrate the effectiveness of DreamPBR in material creation, showcasing its versatility and user-friendliness on a wide range of controllable generation and editing applications.
  arXiv  Detail & Related papers  (2024-04-23T02:04:53Z)
• MaterialSeg3D: Segmenting Dense Materials from 2D Priors for 3D Assets [63.284244910964475]
  We propose a 3D asset material generation framework to infer underlying material from the 2D semantic prior. Based on such a prior model, we devise a mechanism to parse material in 3D space.
  arXiv  Detail & Related papers  (2024-04-22T07:00:17Z)
• L3GO: Language Agents with Chain-of-3D-Thoughts for Generating Unconventional Objects [53.4874127399702]
  We propose a language agent with chain-of-3D-thoughts (L3GO), an inference-time approach that can reason about part-based 3D mesh generation. We develop a new benchmark, Unconventionally Feasible Objects (UFO), as well as SimpleBlenv, a wrapper environment built on top of Blender. Our approach surpasses the standard GPT-4 and other language agents for 3D mesh generation on ShapeNet.
  arXiv  Detail & Related papers  (2024-02-14T09:51:05Z)
• Generating Parametric BRDFs from Natural Language Descriptions [1.1847636087764204]
  We develop a model to generate Bidirectional Reflectance Distribution Functions from descriptive prompts. BRDFs are four dimensional probability distributions that characterize the interaction of light with surface materials. Our model is first trained using a semi-supervised approach before being tuned via an unsupervised scheme.
  arXiv  Detail & Related papers  (2023-06-19T15:35:19Z)
• Generative Modelling of BRDF Textures from Flash Images [50.660026124025265]
  We learn a latent space for easy capture, semantic editing, consistent, and efficient reproduction of visual material appearance. In a second step, conditioned on the material code, our method produces an infinite and diverse spatial field of BRDF model parameters.
  arXiv  Detail & Related papers  (2021-02-23T18:45:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.