CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback

• URL: http://arxiv.org/abs/2504.19860v3
• Date: Wed, 13 Aug 2025 09:30:16 GMT
• Title: CoherenDream: Boosting Holistic Text Coherence in 3D Generation via Multimodal Large Language Models Feedback
• Authors: Chenhan Jiang, Yihan Zeng, Dit-Yan Yeung,
• Abstract summary: Score Distillation Sampling (SDS) has achieved remarkable success in text-to-3D content generation.<n>SDS-based methods struggle to maintain semantic fidelity for user prompts.<n>We propose Textual Coherent Score Distillation (TCSD), which integrates alignment feedback from multimodal large language models (MLLMs)
• Score: 18.857087708269038
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Score Distillation Sampling (SDS) has achieved remarkable success in text-to-3D content generation. However, SDS-based methods struggle to maintain semantic fidelity for user prompts, particularly when involving multiple objects with intricate interactions. While existing approaches often address 3D consistency through multiview diffusion model fine-tuning on 3D datasets, this strategy inadvertently exacerbates text-3D alignment degradation. The limitation stems from SDS's inherent accumulation of view-independent biases during optimization, which progressively diverges from the ideal text alignment direction. To alleviate this limitation, we propose a novel SDS objective, dubbed as Textual Coherent Score Distillation (TCSD), which integrates alignment feedback from multimodal large language models (MLLMs). Our TCSD leverages cross-modal understanding capabilities of MLLMs to assess and guide the text-3D correspondence during the optimization. We further develop 3DLLaVA-CRITIC - a fine-tuned MLLM specialized for evaluating multiview text alignment in 3D generations. Additionally, we introduce an LLM-layout initialization that significantly accelerates optimization convergence through semantic-aware spatial configuration. Our framework, CoherenDream, achieves consistent improvement across multiple metrics on TIFA subset.As the first study to incorporate MLLMs into SDS optimization, we also conduct extensive ablation studies to explore optimal MLLM adaptations for 3D generation tasks.

Related papers

• CG-MLLM: Captioning and Generating 3D content via Multi-modal Large Language Models [18.035268191933117]
  CG-MLLM is a novel Large Language Model capable of 3D captioning and high-resolution 3D generation in a single framework.<n>By integrating a pre-trained vision-language backbone with a specialized 3D VAE latent space, CG-MLLM facilitates long-context interactions between standard tokens and spatial blocks.
  arXiv  Detail & Related papers  (2026-01-29T14:42:46Z)
• Lemon: A Unified and Scalable 3D Multimodal Model for Universal Spatial Understanding [80.66591664266744]
  Lemon is a unified transformer architecture that processes 3D point cloud patches and language tokens as a single sequence.<n>To handle the complexity of 3D data, we develop a structured patchification and tokenization scheme that preserves spatial context.<n>Lemon establishes new state-of-the-art performance across comprehensive 3D understanding and reasoning tasks.
  arXiv  Detail & Related papers  (2025-12-14T20:02:43Z)
• Vid-LLM: A Compact Video-based 3D Multimodal LLM with Reconstruction-Reasoning Synergy [4.1703677379815565]
  We propose Vid-LLM, a video-based 3D-MLLM that directly processes video inputs without requiring external 3D data.<n>In our method, the geometric prior are directly used to improve the performance of the sceen perception.<n>Experiments across diverse benchmarks verified the effectiveness of our method on 3D Question Answering, 3D Captioning and 3D Visual Grounding tasks.
  arXiv  Detail & Related papers  (2025-09-29T07:34:18Z)
• Vision-Language Models as Differentiable Semantic and Spatial Rewards for Text-to-3D Generation [23.359745449828363]
  We propose VLM3D, a novel text-to-3D generation framework.<n>It integrates large vision-language models into the Score Distillation Sampling pipeline as differentiable semantic and spatial priors.<n>VLM3D significantly outperforms prior SDS-based methods in semantic fidelity, geometric coherence, and spatial correctness.
  arXiv  Detail & Related papers  (2025-09-19T08:54:52Z)
• MeshLLM: Empowering Large Language Models to Progressively Understand and Generate 3D Mesh [79.20802127426003]
  MeshLLM is a framework that leverages large language models (LLMs) to understand and generate text-serialized 3D meshes.<n>We introduce a Primitive-Mesh decomposition strategy, which divides 3D meshes into structurally meaningful subunits.<n> Experiments show that MeshLLM outperforms the state-of-the-art LLaMA-Mesh in both mesh generation quality and shape understanding.
  arXiv  Detail & Related papers  (2025-08-02T07:37:37Z)
• LayoutVLM: Differentiable Optimization of 3D Layout via Vision-Language Models [57.92316645992816]
  Spatial reasoning is a fundamental aspect of human cognition, enabling intuitive understanding and manipulation of objects in three-dimensional space.<n>We introduce LayoutVLM, a framework and scene layout representation that exploits the semantic knowledge of Vision-Language Models (VLMs)<n>We demonstrate that fine-tuning VLMs with the proposed scene layout representation extracted from existing scene datasets can improve their reasoning performance.
  arXiv  Detail & Related papers  (2024-12-03T06:15:04Z)
• TV-3DG: Mastering Text-to-3D Customized Generation with Visual Prompt [41.880416357543616]
  We propose a novel algorithm, Score Matching (CSM), which removes the difference term in Score Distillation Sampling (SDS) We integrate visual prompt information with an attention fusion mechanism and sampling guidance techniques, forming the Visual Prompt CSM algorithm. We present our approach as TV-3DG, with extensive experiments demonstrating its capability to achieve stable, high-quality, customized 3D generation.
  arXiv  Detail & Related papers  (2024-10-16T07:13:09Z)
• Semantic Score Distillation Sampling for Compositional Text-to-3D Generation [28.88237230872795]
  Generating high-quality 3D assets from textual descriptions remains a pivotal challenge in computer graphics and vision research. We introduce a novel SDS approach, designed to improve the expressiveness and accuracy of compositional text-to-3D generation. Our approach integrates new semantic embeddings that maintain consistency across different rendering views. By leveraging explicit semantic guidance, our method unlocks the compositional capabilities of existing pre-trained diffusion models.
  arXiv  Detail & Related papers  (2024-10-11T17:26:00Z)
• SeMv-3D: Towards Concurrency of Semantic and Multi-view Consistency in General Text-to-3D Generation [122.47961178994456]
  SeMv-3D is a novel framework that jointly enhances semantic alignment and multi-view consistency in GT23D generation.<n>At its core, we introduce Triplane Prior Learning (TPL), which effectively learns triplane priors.<n>We also present Prior-based Semantic Aligning in Triplanes (SAT), which enables consistent any-view synthesis.
  arXiv  Detail & Related papers  (2024-10-10T07:02:06Z)
• MVGaussian: High-Fidelity text-to-3D Content Generation with Multi-View Guidance and Surface Densification [13.872254142378772]
  This paper introduces a unified framework for text-to-3D content generation. Our approach utilizes multi-view guidance to iteratively form the structure of the 3D model. We also introduce a novel densification algorithm that aligns gaussians close to the surface.
  arXiv  Detail & Related papers  (2024-09-10T16:16:34Z)
• MMScan: A Multi-Modal 3D Scene Dataset with Hierarchical Grounded Language Annotations [55.022519020409405]
  This paper builds the first largest ever multi-modal 3D scene dataset and benchmark with hierarchical grounded language annotations, MMScan. The resulting multi-modal 3D dataset encompasses 1.4M meta-annotated captions on 109k objects and 7.7k regions as well as over 3.04M diverse samples for 3D visual grounding and question-answering benchmarks.
  arXiv  Detail & Related papers  (2024-06-13T17:59:30Z)
• VP-LLM: Text-Driven 3D Volume Completion with Large Language Models through Patchification [56.211321810408194]
  Large language models (LLMs) have shown great potential in multi-modal understanding and generation tasks. We present Volume Patch LLM (VP-LLM), which leverages LLMs to perform conditional 3D completion in a single-forward pass. Our results demonstrate a strong ability of LLMs to interpret complex text instructions and understand 3D objects, surpassing state-of-the-art diffusion-based 3D completion models in generation quality.
  arXiv  Detail & Related papers  (2024-06-08T18:17:09Z)
• Grounded Compositional and Diverse Text-to-3D with Pretrained Multi-View Diffusion Model [65.58911408026748]
  We propose Grounded-Dreamer to generate 3D assets that can accurately follow complex, compositional text prompts. We first advocate leveraging text-guided 4-view images as the bottleneck in the text-to-3D pipeline. We then introduce an attention refocusing mechanism to encourage text-aligned 4-view image generation.
  arXiv  Detail & Related papers  (2024-04-28T04:05:10Z)
• Beyond First Impressions: Integrating Joint Multi-modal Cues for Comprehensive 3D Representation [72.94143731623117]
  Existing methods simply align 3D representations with single-view 2D images and coarse-grained parent category text. Insufficient synergy neglects the idea that a robust 3D representation should align with the joint vision-language space. We propose a multi-view joint modality modeling approach, termed JM3D, to obtain a unified representation for point cloud, text, and image.
  arXiv  Detail & Related papers  (2023-08-06T01:11:40Z)

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.