SF3D: Stable Fast 3D Mesh Reconstruction with UV-unwrapping and Illumination Disentanglement
Mark Boss, Zixuan Huang, Aaryaman Vasishta, Varun Jampani
摘要
We present SF3D, a novel method for rapid and high-quality textured object mesh reconstruction from a single image in just 0.3 seconds. Unlike most existing approaches, SF3D is explicitly trained for mesh generation, incorporating a fast UV unwrapping technique that enables swift texture generation rather than relying on vertex colors. The method also learns to predict material parameters and normal maps to enhance the visual quality of the reconstructed 3D meshes. Furthermore, SF3D integrates a delighting step to effectively remove low-frequency illumination effects, ensuring that the reconstructed meshes can be easily used in novel illumination conditions. Experiments demonstrate the superior performance of SF3D over the existing techniques.Project page with code and model: https://stable-fast-3d.github.io
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。
引用它的顶会 Paper36
- MeshSplatting: Differentiable Rendering with Opaque MeshesJan Held, Sanghyun Son, Renaud Vandeghen, Daniel Rebain 等CVPR 2026 · 被引用 25 次
- ImaginateAR: AI-Assisted In-Situ Authoring in Augmented RealityJaewook Lee, Filippo Aleotti, Diego Mazala, Guillermo Garcia-Hernando 等UIST 2025 · 被引用 15 次
- GaSLight: Gaussian Splats for Spatially-Varying Lighting in HDRChristophe Bolduc, Yannick Hold-Geoffroy, Jean-François LalondeICCV 2025 · 被引用 14 次
- FreeSplatter: Pose-free Gaussian Splatting for Sparse-view 3D ReconstructionJiale Xu, Shenghua Gao, Ying ShanICCV 2025 · 被引用 8 次
- Not All Views Are Created Equal: Analyzing Viewpoint Instabilities in Vision Foundation ModelsMateusz Michalkiewicz, Sheena Bai, Mahsa Baktashmotlagh, Varun Jampani 等ICCV 2025 · 被引用 8 次
它引用的顶会 Paper41
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh 等ICML 2021 · 被引用 47,906 次
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 被引用 35,902 次
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser 等CVPR 2022 · 被引用 13,123 次
- Emerging Properties in Self-Supervised Vision TransformersMathilde Caron, Hugo Touvron, Ishan Misra, Hervé Jégou 等ICCV 2021 · 被引用 8,921 次
- 3D Gaussian Splatting for Real-Time Radiance Field RenderingBernhard Kerbl, Georgios Kopanas, Thomas Leimkühler, George DrettakisSIGGRAPH 2023 · 被引用 5,687 次
相关 Paper
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape OptimizationMinghua Liu, Chao Xu, Haian Jin, Linghao Chen 等NeurIPS 2023 · 被引用 755 次
- SPAR3D: Stable Point-Aware Reconstruction of 3D Objects from Single ImagesZixuan Huang, Mark Boss, Aaryaman Vasishta, James M. Rehg 等CVPR 2025
- Unique3D: High-Quality and Efficient 3D Mesh Generation from a Single ImageKailu Wu, Fangfu Liu, Zhihan Cai, Runjie Yan 等NeurIPS 2024 · 被引用 185 次
- Magic123: One Image to High-Quality 3D Object Generation Using Both 2D and 3D Diffusion PriorsGuocheng Qian, Jinjie Mai, Abdullah Hamdi, Jian Ren 等ICLR 2024 · 被引用 444 次
- UV-free Texture Generation with Denoising and Geodesic Heat DiffusionSimone Foti, Stefanos Zafeiriou, Tolga BirdalNeurIPS 2024 · 被引用 5 次
