SeMv-3D: Towards Semantic and Mutil-view Consistency simultaneously for General Text-to-3D Generation with Triplane Priors

• URL: http://arxiv.org/abs/2410.07658v1
• Date: Thu, 10 Oct 2024 07:02:06 GMT
• Title: SeMv-3D: Towards Semantic and Mutil-view Consistency simultaneously for General Text-to-3D Generation with Triplane Priors
• Authors: Xiao Cai, Pengpeng Zeng, Lianli Gao, Junchen Zhu, Jiaxin Zhang, Sitong Su, Heng Tao Shen, Jingkuan Song,
• Abstract summary: We propose SeMv-3D, a novel framework for general text-to-3d generation. We propose a Triplane Prior Learner that learns triplane priors with 3D spatial features to maintain consistency among different views at the 3D level. We also design a Semantic-aligned View Synthesizer that preserves the alignment between 3D spatial features and textual semantics in latent space.
• Score: 115.66850201977887
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent advancements in generic 3D content generation from text prompts have been remarkable by fine-tuning text-to-image diffusion (T2I) models or employing these T2I models as priors to learn a general text-to-3D model. While fine-tuning-based methods ensure great alignment between text and generated views, i.e., semantic consistency, their ability to achieve multi-view consistency is hampered by the absence of 3D constraints, even in limited view. In contrast, prior-based methods focus on regressing 3D shapes with any view that maintains uniformity and coherence across views, i.e., multi-view consistency, but such approaches inevitably compromise visual-textual alignment, leading to a loss of semantic details in the generated objects. To achieve semantic and multi-view consistency simultaneously, we propose SeMv-3D, a novel framework for general text-to-3d generation. Specifically, we propose a Triplane Prior Learner (TPL) that learns triplane priors with 3D spatial features to maintain consistency among different views at the 3D level, e.g., geometry and texture. Moreover, we design a Semantic-aligned View Synthesizer (SVS) that preserves the alignment between 3D spatial features and textual semantics in latent space. In SVS, we devise a simple yet effective batch sampling and rendering strategy that can generate arbitrary views in a single feed-forward inference. Extensive experiments present our SeMv-3D's superiority over state-of-the-art performances with semantic and multi-view consistency in any view. Our code and more visual results are available at https://anonymous.4open.science/r/SeMv-3D-6425.

Related papers

• Weakly-Supervised 3D Visual Grounding based on Visual Linguistic Alignment [26.858034573776198]
  We propose a weakly supervised approach for 3D visual grounding based on Visual Linguistic Alignment. Our 3D-VLA exploits the superior ability of current large-scale vision-language models on aligning the semantics between texts and 2D images. During the inference stage, the learned text-3D correspondence will help us ground the text queries to the 3D target objects even without 2D images.
  arXiv  Detail & Related papers  (2023-12-15T09:08:14Z)
• 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)
• Sculpting Holistic 3D Representation in Contrastive Language-Image-3D Pre-training [51.632418297156605]
  We introduce MixCon3D, a method aiming to sculpt holistic 3D representation in contrastive language-image-3D pre-training. We develop the 3D object-level representation from complementary perspectives, e.g., multi-view rendered images with the point cloud. Then, MixCon3D performs language-3D contrastive learning, comprehensively depicting real-world 3D objects and bolstering text alignment.
  arXiv  Detail & Related papers  (2023-11-03T06:05:36Z)
• T$^3$Bench: Benchmarking Current Progress in Text-to-3D Generation [52.029698642883226]
  Methods in text-to-3D leverage powerful pretrained diffusion models to optimize NeRF. Most studies evaluate their results with subjective case studies and user experiments. We introduce T$3$Bench, the first comprehensive text-to-3D benchmark.
  arXiv  Detail & Related papers  (2023-10-04T17:12:18Z)
• Chasing Consistency in Text-to-3D Generation from a Single Image [35.60887743544786]
  We present Consist3D, a three-stage framework Chasing for semantic-, geometric-, and saturation-Consistent Text-to-3D generation from a single image. Specifically, the semantic encoding stage learns a token independent of views and estimations, promoting semantic consistency and robustness. The geometric encoding stage learns another token with comprehensive geometry and reconstruction constraints under novel-view estimations, reducing overfitting and encouraging geometric consistency.
  arXiv  Detail & Related papers  (2023-09-07T09:50:48Z)
• ViewRefer: Grasp the Multi-view Knowledge for 3D Visual Grounding with GPT and Prototype Guidance [48.748738590964216]
  We propose ViewRefer, a multi-view framework for 3D visual grounding. For the text branch, ViewRefer expands a single grounding text to multiple geometry-consistent descriptions. In the 3D modality, a transformer fusion module with inter-view attention is introduced to boost the interaction of objects across views.
  arXiv  Detail & Related papers  (2023-03-29T17:59:10Z)

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.