paper-with-me

홈 › Papers

Align 3D Representation and Text Embedding for 3D Content Personalization

2025-08-23 · Qi Song, Ziyuan Luo, Ka Chun Cheung, Simon See, Renjie Wan arxiv

Recent advances in NeRF and 3DGS have significantly enhanced the efficiency and quality of 3D content synthesis. However, efficient personalization of generated 3D content remains a critical challenge. Current 3D personalization approaches predominantly rely on knowledge distillation-based methods, which require computationally expensive retraining procedures. To address this challenge, we propose \textbf{Invert3D}, a novel framework for convenient 3D content personalization. Nowadays, vision-language models such as CLIP enable direct image personalization through aligned vision-text embedding spaces. However, the inherent structural differences between 3D content and 2D images preclude direct application of these techniques to 3D personalization. Our approach bridges this gap by establishing alignment between 3D representations and text embedding spaces. Specifically, we develop a camera-conditioned 3D-to-text inverse mechanism that projects 3D contents into a 3D embedding aligned with text embeddings. This alignment enables efficient manipulation and personalization of 3D content through natural language prompts, eliminating the need for computationally retraining procedures. Extensive experiments demonstrate that Invert3D achieves effective personalization of 3D content. Our work is available at: https://github.com/qsong2001/Invert3D.

📄 PDF Abstract BibTeX arXiv:2508.16932

Code (0)

등록된 구현이 없습니다.

Tasks

Knowledge Distillation

Similar Papers 제목 키워드 기반

Highly Personalized Text Embedding for Image Manipulation by Stable Diffusion

2023-03-15 · Inhwa Han, Serin Yang, Taesung Kwon, Jong Chul Ye

Diffusion models have shown superior performance in image generation and manipulation, but the inherent stochasticity presents challenges in preserving and manipulating image content and identity. While previous approach…

Image GenerationImage Manipulation

Embedding-Based Rankings of Educational Resources based on Learning Outcome Alignment: Benchmarking, Expert Validation, and Learner Performance

2025-12-15 · Mohammadreza Molavi, Mohammad Moein, Mohammadreza Tavakoli, Abdolali Faraji 외 arxiv

As the online learning landscape evolves, the need for personalization is increasingly evident. Although educational resources are burgeoning, educators face challenges selecting materials that both align with intended l…

Molar: Multimodal LLMs with Collaborative Filtering Alignment for Enhanced Sequential Recommendation

2024-12-24 · Yucong Luo, Qitao Qin, Hao Zhang, Mingyue Cheng 외

Sequential recommendation (SR) systems have evolved significantly over the past decade, transitioning from traditional collaborative filtering to deep learning approaches and, more recently, to large language models (LLM…

Collaborative FilteringSequential Recommendation

Towards Graph Foundation Models for Personalization

2024-03-12 · Andreas Damianou, Francesco Fabbri, Paul Gigioli, Marco De Nadai 외

In the realm of personalization, integrating diverse information sources such as consumption signals and content-based representations is becoming increasingly critical to build state-of-the-art solutions. In this regard…

Language ModellingLarge Language ModelSpecificity

Reflective Personalization Optimization: A Post-hoc Rewriting Framework for Black-Box Large Language Models

2025-11-07 · Teqi Hao, Xioayu Tan, Shaojie Shi, Yinghui Xu 외 arxiv

The personalization of black-box large language models (LLMs) is a critical yet challenging task. Existing approaches predominantly rely on context injection, where user history is embedded into the prompt to directly gu…

Reinforcement Learning