MS3D: High-Quality 3D Generation via Multi-Scale Representation Modeling
Guan Luo, Jianfeng Zhang
2025年份
1被引次数
摘要
Multi-Scale Feature Figure 1. Previous methods rely on single-scale reconstruction, requiring the model to capture both global structure and local details simultaneously, often leading to suboptimal results. In contrast, our method decomposes the reconstruction process into progressive refinement, enabling more precise geometric and texture generation.
问问这篇 Paper
智能体会读完全文。
Lune 把这篇 Paper 索引到了每一个公式,引用它的顶会 Paper 也一样。你提问,回答直接引用原文。
它引用的顶会 Paper49
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
- Instant neural graphics primitives with a multiresolution hash encodingThomas Müller, Alex Evans, Christoph Schied, Alexander KellerSIGGRAPH 2022 · 被引用 4,089 次
- Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radiance FieldsJonathan T. Barron, Ben Mildenhall, Matthew Tancik, Peter Hedman 等ICCV 2021 · 被引用 2,700 次
- Vision Transformers for Dense PredictionRené Ranftl, Alexey Bochkovskiy, Vladlen KoltunICCV 2021 · 被引用 2,647 次
相关 Paper
- Generative Densification: Learning to Densify Gaussians for High-Fidelity Generalizable 3D ReconstructionSeungtae Nam, Xiangyu Sun, Gyeongjin Kang, Younggeun Lee 等CVPR 2025
- WonderZoom: Multi-Scale 3D World GenerationJin Cao, Hong-Xing Yu, Jiajun WuCVPR 2026 · 被引用 1 次
- View Generalization for Single Image Textured 3D ModelsAnand Bhattad, Aysegul Dundar, Guilin Liu, Andrew Tao 等CVPR 2021
- Robust-MVTON: Learning Cross-Pose Feature Alignment and Fusion for Robust Multi-View Virtual Try-OnNannan Zhang, Yijiang Li, Dong Du, Zheng Chong 等CVPR 2025
- VisFusion: Visibility-Aware Online 3D Scene Reconstruction from VideosHuiyu Gao, Wei Mao, Miaomiao LiuCVPR 2023
