End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards

• URL: http://arxiv.org/abs/2506.18331v2
• Date: Sat, 26 Jul 2025 05:53:42 GMT
• Title: End-to-End Fine-Tuning of 3D Texture Generation using Differentiable Rewards
• Authors: AmirHossein Zamani, Tianhao Xie, Amir G. Aghdam, Tiberiu Popa, Eugene Belilovsky,
• Abstract summary: We propose an end-to-end differentiable, reinforcement-learning-free framework that embeds human feedback, expressed as differentiable reward functions, directly into the 3D texture pipeline.<n>By back-propagating preference signals through both geometric and appearance modules, our method generates textures that respect the 3D geometry structure and align with desired criteria.
• Score: 8.953379216683732
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: While recent 3D generative models can produce high-quality texture images, they often fail to capture human preferences or meet task-specific requirements. Moreover, a core challenge in the 3D texture generation domain is that most existing approaches rely on repeated calls to 2D text-to-image generative models, which lack an inherent understanding of the 3D structure of the input 3D mesh object. To alleviate these issues, we propose an end-to-end differentiable, reinforcement-learning-free framework that embeds human feedback, expressed as differentiable reward functions, directly into the 3D texture synthesis pipeline. By back-propagating preference signals through both geometric and appearance modules of the proposed framework, our method generates textures that respect the 3D geometry structure and align with desired criteria. To demonstrate its versatility, we introduce three novel geometry-aware reward functions, which offer a more controllable and interpretable pathway for creating high-quality 3D content from natural language. By conducting qualitative, quantitative, and user-preference evaluations against state-of-the-art methods, we demonstrate that our proposed strategy consistently outperforms existing approaches. We will make our implementation code publicly available upon acceptance of the paper.

Related papers

• RomanTex: Decoupling 3D-aware Rotary Positional Embedded Multi-Attention Network for Texture Synthesis [10.350576861948952]
  RomanTex is a multiview-based texture generation framework that integrates a multi-attention network with an underlying 3D representation.<n>Our method achieves state-of-the-art results in texture quality and consistency.
  arXiv  Detail & Related papers  (2025-03-24T17:56:11Z)
• Pandora3D: A Comprehensive Framework for High-Quality 3D Shape and Texture Generation [56.862552362223425]
  This report presents a comprehensive framework for generating high-quality 3D shapes and textures from diverse input prompts.<n>The framework consists of 3D shape generation and texture generation.<n>This report details the system architecture, experimental results, and potential future directions to improve and expand the framework.
  arXiv  Detail & Related papers  (2025-02-20T04:22:30Z)
• Learning 3D Representations from Procedural 3D Programs [6.915871213703219]
  We propose learning 3D representations from procedural 3D programs that automatically generate 3D shapes using simple primitives and augmentations.<n>Remarkably, the 3D representations learned from the procedurally generated 3D shapes perform on par with state-of-the-art representations learned from semantically recognizable 3D models.
  arXiv  Detail & Related papers  (2024-11-25T18:59:57Z)
• GaussianAnything: Interactive Point Cloud Flow Matching For 3D Object Generation [75.39457097832113]
  This paper introduces a novel 3D generation framework, offering scalable, high-quality 3D generation with an interactive Point Cloud-structured Latent space.<n>Our framework employs a Variational Autoencoder with multi-view posed RGB-D(epth)-N(ormal) renderings as input, using a unique latent space design that preserves 3D shape information.<n>The proposed method, GaussianAnything, supports multi-modal conditional 3D generation, allowing for point cloud, caption, and single image inputs.
  arXiv  Detail & Related papers  (2024-11-12T18:59:32Z)
• DreamPolish: Domain Score Distillation With Progressive Geometry Generation [66.94803919328815]
  We introduce DreamPolish, a text-to-3D generation model that excels in producing refined geometry and high-quality textures. In the geometry construction phase, our approach leverages multiple neural representations to enhance the stability of the synthesis process. In the texture generation phase, we introduce a novel score distillation objective, namely domain score distillation (DSD), to guide neural representations toward such a domain.
  arXiv  Detail & Related papers  (2024-11-03T15:15:01Z)
• DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D Data [50.164670363633704]
  We present DIRECT-3D, a diffusion-based 3D generative model for creating high-quality 3D assets from text prompts. Our model is directly trained on extensive noisy and unaligned in-the-wild' 3D assets. We achieve state-of-the-art performance in both single-class generation and text-to-3D generation.
  arXiv  Detail & Related papers  (2024-06-06T17:58:15Z)
• 3D-SceneDreamer: Text-Driven 3D-Consistent Scene Generation [51.64796781728106]
  We propose a generative refinement network to synthesize new contents with higher quality by exploiting the natural image prior to 2D diffusion model and the global 3D information of the current scene. Our approach supports wide variety of scene generation and arbitrary camera trajectories with improved visual quality and 3D consistency.
  arXiv  Detail & Related papers  (2024-03-14T14:31:22Z)
• En3D: An Enhanced Generative Model for Sculpting 3D Humans from 2D Synthetic Data [36.51674664590734]
  We present En3D, an enhanced izable scheme for high-qualityd 3D human avatars. Unlike previous works that rely on scarce 3D datasets or limited 2D collections with imbalance viewing angles and pose priors, our approach aims to develop a zero-shot 3D capable of producing 3D humans.
  arXiv  Detail & Related papers  (2024-01-02T12:06:31Z)
• Guide3D: Create 3D Avatars from Text and Image Guidance [55.71306021041785]
  Guide3D is a text-and-image-guided generative model for 3D avatar generation based on diffusion models. Our framework produces topologically and structurally correct geometry and high-resolution textures.
  arXiv  Detail & Related papers  (2023-08-18T17:55:47Z)
• High-fidelity 3D GAN Inversion by Pseudo-multi-view Optimization [51.878078860524795]
  We present a high-fidelity 3D generative adversarial network (GAN) inversion framework that can synthesize photo-realistic novel views. Our approach enables high-fidelity 3D rendering from a single image, which is promising for various applications of AI-generated 3D content.
  arXiv  Detail & Related papers  (2022-11-28T18:59:52Z)
• GET3D: A Generative Model of High Quality 3D Textured Shapes Learned from Images [72.15855070133425]
  We introduce GET3D, a Generative model that directly generates Explicit Textured 3D meshes with complex topology, rich geometric details, and high-fidelity textures. GET3D is able to generate high-quality 3D textured meshes, ranging from cars, chairs, animals, motorbikes and human characters to buildings.
  arXiv  Detail & Related papers  (2022-09-22T17:16:19Z)
• 3DStyleNet: Creating 3D Shapes with Geometric and Texture Style Variations [81.45521258652734]
  We propose a method to create plausible geometric and texture style variations of 3D objects. Our method can create many novel stylized shapes, resulting in effortless 3D content creation and style-ware data augmentation.
  arXiv  Detail & Related papers  (2021-08-30T02:28:31Z)
• Convolutional Generation of Textured 3D Meshes [34.20939983046376]
  We propose a framework that can generate triangle meshes and associated high-resolution texture maps, using only 2D supervision from single-view natural images. A key contribution of our work is the encoding of the mesh and texture as 2D representations, which are semantically aligned and can be easily modeled by a 2D convolutional GAN. We demonstrate the efficacy of our method on Pascal3D+ Cars and CUB, both in an unconditional setting and in settings where the model is conditioned on class labels, attributes, and text.
  arXiv  Detail & Related papers  (2020-06-13T15:23:29Z)

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.