CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization

• URL: http://arxiv.org/abs/2603.19121v2
• Date: Fri, 20 Mar 2026 03:34:53 GMT
• Title: CustomTex: High-fidelity Indoor Scene Texturing via Multi-Reference Customization
• Abstract summary: Text-driven methods offer flexibility, fine instance-level control, and often produce textures with insufficient quality.<n>We introduce CustomTex, a novel framework for instance-level editing.
• Score: 36.4737529204489
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The creation of high-fidelity, customizable 3D indoor scene textures remains a significant challenge. While text-driven methods offer flexibility, they lack the precision for fine-grained, instance-level control, and often produce textures with insufficient quality, artifacts, and baked-in shading. To overcome these limitations, we introduce CustomTex, a novel framework for instance-level, high-fidelity scene texturing driven by reference images. CustomTex takes an untextured 3D scene and a set of reference images specifying the desired appearance for each object instance, and generates a unified, high-resolution texture map. The core of our method is a dual-distillation approach that separates semantic control from pixel-level enhancement. We employ semantic-level distillation, equipped with an instance cross-attention, to ensure semantic plausibility and ``reference-instance'' alignment, and pixel-level distillation to enforce high visual fidelity. Both are unified within a Variational Score Distillation (VSD) optimization framework. Experiments demonstrate that CustomTex achieves precise instance-level consistency with reference images and produces textures with superior sharpness, reduced artifacts, and minimal baked-in shading compared to state-of-the-art methods. Our work establishes a more direct and user-friendly path to high-quality, customizable 3D scene appearance editing.

Related papers

• Controllable Texture Tiling with Transformed RoPE-Enhanced Diffusion Models [21.26349994452928]
  We propose a novel framework for controllable and high-fidelity texture tiling based on Diffusion Transformers.<n>Our approach introduces two key technical innovations to decouple spatial manipulation from content generation.<n>Our method outperforms state-of-the-art baselines in both control accuracy and texture fidelity.
  arXiv  Detail & Related papers  (2026-06-22T07:24:15Z)
• ZeroScene: A Zero-Shot Framework for 3D Scene Generation from a Single Image and Controllable Texture Editing [36.098009720325436]
  We propose a novel system to accomplish both single image-to-3D scene reconstruction and texture editing in a zero-shot manner.<n>ZeroScene extracts object-level 2D segmentation and depth information from input images to infer spatial relationships within the scene.<n>It then jointly optimize 3D and 2D projection losses of the point cloud to update object poses for precise scene alignment.
  arXiv  Detail & Related papers  (2025-09-28T03:21:12Z)
• A Scalable Attention-Based Approach for Image-to-3D Texture Mapping [3.8476192001237597]
  High-quality textures are critical for realistic 3D content creation.<n>Existing generative methods are slow, rely on UV maps, and often fail to remain faithful to a reference image.<n>We propose a transformer-based framework that predicts a 3D texture field directly from a single image and a mesh.
  arXiv  Detail & Related papers  (2025-09-05T14:18:52Z)
• TriTex: Learning Texture from a Single Mesh via Triplane Semantic Features [78.13246375582906]
  We present a novel approach that learns a volumetric texture field from a single textured mesh by mapping semantic features to surface target colors.<n>Our approach achieves superior texture quality across 3D models in applications like game development.
  arXiv  Detail & Related papers  (2025-03-20T18:35:03Z)
• RoomTex: Texturing Compositional Indoor Scenes via Iterative Inpainting [34.827355403635536]
  We propose a 3D scene framework referred to as RoomTex. RoomTex generates high-fidelity and style-consistent textures for un-consistent scene meshes. We propose to maintain superior alignment between RGB and edge detection methods.
  arXiv  Detail & Related papers  (2024-06-04T16:27:09Z)
• EucliDreamer: Fast and High-Quality Texturing for 3D Models with Depth-Conditioned Stable Diffusion [5.158983929861116]
  We present EucliDreamer, a simple and effective method to generate textures for 3D models given text and prompts. The texture is parametized as an implicit function on the 3D surface, which is optimized with the Score Distillation Sampling (SDS) process and differentiable rendering.
  arXiv  Detail & Related papers  (2024-04-16T04:44:16Z)
• TextureDreamer: Image-guided Texture Synthesis through Geometry-aware Diffusion [64.49276500129092]
  TextureDreamer is an image-guided texture synthesis method. It can transfer relightable textures from a small number of input images to target 3D shapes across arbitrary categories.
  arXiv  Detail & Related papers  (2024-01-17T18:55:49Z)
• SceneWiz3D: Towards Text-guided 3D Scene Composition [134.71933134180782]
  Existing approaches either leverage large text-to-image models to optimize a 3D representation or train 3D generators on object-centric datasets. We introduce SceneWiz3D, a novel approach to synthesize high-fidelity 3D scenes from text.
  arXiv  Detail & Related papers  (2023-12-13T18:59:30Z)
• TeMO: Towards Text-Driven 3D Stylization for Multi-Object Meshes [67.5351491691866]
  We present a novel framework, dubbed TeMO, to parse multi-object 3D scenes and edit their styles. Our method can synthesize high-quality stylized content and outperform the existing methods over a wide range of multi-object 3D meshes.
  arXiv  Detail & Related papers  (2023-12-07T12:10:05Z)
• SceneTex: High-Quality Texture Synthesis for Indoor Scenes via Diffusion Priors [49.03627933561738]
  SceneTex is a novel method for generating high-quality and style-consistent textures for indoor scenes using depth-to-image diffusion priors. SceneTex enables various and accurate texture synthesis for 3D-FRONT scenes, demonstrating significant improvements in visual quality and prompt fidelity over the prior texture generation methods.
  arXiv  Detail & Related papers  (2023-11-28T22:49:57Z)
• SceneComposer: Any-Level Semantic Image Synthesis [80.55876413285587]
  We propose a new framework for conditional image synthesis from semantic layouts of any precision levels. The framework naturally reduces to text-to-image (T2I) at the lowest level with no shape information, and it becomes segmentation-to-image (S2I) at the highest level. We introduce several novel techniques to address the challenges coming with this new setup.
  arXiv  Detail & Related papers  (2022-11-21T18:59:05Z)

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.