paper-with-me

Papers

DiffSplat: Repurposing Image Diffusion Models for Scalable Gaussian Splat Generation

2025-01-28 · Chenguo Lin, Panwang Pan, Bangbang Yang, Zeming Li, Yadong Mu

Recent advancements in 3D content generation from text or a single image struggle with limited high-quality 3D datasets and inconsistency from 2D multi-view generation. We introduce DiffSplat, a novel 3D generative framework that natively generates 3D Gaussian splats by taming large-scale text-to-image diffusion models. It differs from previous 3D generative models by effectively utilizing web-scale 2D priors while maintaining 3D consistency in a unified model. To bootstrap the training, a lightweight reconstruction model is proposed to instantly produce multi-view Gaussian splat grids for scalable dataset curation. In conjunction with the regular diffusion loss on these grids, a 3D rendering loss is introduced to facilitate 3D coherence across arbitrary views. The compatibility with image diffusion models enables seamless adaptions of numerous techniques for image generation to the 3D realm. Extensive experiments reveal the superiority of DiffSplat in text- and image-conditioned generation tasks and downstream applications. Thorough ablation studies validate the efficacy of each critical design choice and provide insights into the underlying mechanism.

📄 PDF Abstract BibTeX arXiv:2501.16764

Code (1)

chenguolin/DiffSplat pytorch

Tasks

3D Generation

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

Repurposing 2D Diffusion Models with Gaussian Atlas for 3D Generation

2025-03-20 · Tiange Xiang, Kai Li, Chengjiang Long, Christian Häne 외

Recent advances in text-to-image diffusion models have been driven by the increasing availability of paired 2D data. However, the development of 3D diffusion models has been hindered by the scarcity of high-quality 3D da…

3D GenerationTransfer Learning

Kiss3DGen: Repurposing Image Diffusion Models for 3D Asset Generation

2025-03-03 · CVPR 2025 1 · Jiantao Lin, Xin Yang, Meixi Chen, YingJie Xu 외

Diffusion models have achieved great success in generating 2D images. However, the quality and generalizability of 3D content generation remain limited. State-of-the-art methods often require large-scale 3D assets for tr…

3D Generation3D ReconstructionImage GenerationImage to 3D+1

Heavy-Tailed Diffusion Models

2024-10-18 · Kushagra Pandey, Jaideep Pathak, Yilun Xu, Stephan Mandt 외

Diffusion models achieve state-of-the-art generation quality across many applications, but their ability to capture rare or extreme events in heavy-tailed distributions remains unclear. In this work, we show that traditi…

Denoising

Text2Stereo: Repurposing Stable Diffusion for Stereo Generation with Consistency Rewards

2025-05-27 · Aakash Garg, Libing Zeng, Andrii Tsarov, Nima Khademi Kalantari

In this paper, we propose a novel diffusion-based approach to generate stereo images given a text prompt. Since stereo image datasets with large baselines are scarce, training a diffusion model from scratch is not feasib…

FLUX3D: High-Fidelity 3D Gaussian Generation with Diffusion-Aligned Sparse Representation

2026-06-23 · Haorui Ji, Weizhe Liu, Hongdong Li, Hengkai Guo arxiv

Sparse voxel representation has emerged as a scalable foundation for image-to-3D Gaussian Splatting (3DGS) generation, yet current methods struggle to preserve high-frequency visual details of input images due to two str…

Representation Learning