RealFusion 360° Reconstruction of Any Object from a Single Image
Luke Melas-Kyriazi, Iro Laina, Christian Rupprecht, Andrea Vedaldi
Abstract
https://lukemelas.github.io/realfusion Figure 1. RealFusion generates a full 360 • reconstruction of any object given a single image of it (left column). It does so by leveraging an existing diffusion-based 2D image generator. From the given image, it synthesizes a prompt that causes the diffusion model to "dream up" other views of the object. It then extracts a neural radiance field from the original image and the diffusion model-based prior, thereby reconstructing the object in full. Both appearance and geometry are reconstructed faithfully and extrapolated in a plausible manner.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext ea5a1274-9c52-4c6b-afa7-e63bf2e7ef31Cited by top-tier papers59
- Zero-1-to-3: Zero-shot One Image to 3D ObjectRuoshi Liu, Rundi Wu, Basile Van Hoorick, Pavel Tokmakov et al.ICCV 2023 · 1,662 citations
- Instruct-NeRF2NeRF: Editing 3D Scenes with InstructionsAyaan Haque, Matthew Tancik, Alexei A. Efros, Aleksander Holynski et al.ICCV 2023 · 544 citations
- Instant3D: Fast Text-to-3D with Sparse-view Generation and Large Reconstruction ModelJiahao Li, Hao Tan, Kai Zhang, Zexiang Xu et al.ICLR 2024 · 408 citations
- Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image ModelsLukas Höllein, Ang Cao, Andrew Owens, Justin Johnson et al.ICCV 2023 · 292 citations
- DreamBooth3D: Subject-Driven Text-to-3D GenerationAmit Raj, Srinivas Kaza, Ben Poole, Michael Niemeyer et al.ICCV 2023 · 280 citations
Builds on30
- Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
- Denoising Diffusion Probabilistic ModelsJonathan Ho, Ajay Jain, Pieter AbbeelNeurIPS 2020 · 35,902 citations
- Diffusion Models Beat GANs on Image SynthesisPrafulla Dhariwal, Alexander Quinn NicholNeurIPS 2021 · 13,211 citations
- High-Resolution Image Synthesis with Latent Diffusion ModelsRobin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser et al.CVPR 2022 · 13,123 citations
- Photorealistic Text-to-Image Diffusion Models with Deep Language UnderstandingChitwan Saharia, William Chan, Saurabh Saxena, Lala Li et al.NeurIPS 2022 · 8,965 citations
Related papers
- One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape OptimizationMinghua Liu, Chao Xu, Haian Jin, Linghao Chen et al.NeurIPS 2023 · 755 citations
- ReconFusion: 3D Reconstruction with Diffusion PriorsRundi Wu, Ben Mildenhall, Philipp Henzler, Keunhong Park et al.CVPR 2024 · 137 citations
- Make-It-3D: High-Fidelity 3D Creation from A Single Image with Diffusion PriorJunshu Tang, Tengfei Wang, Bo Zhang, Ting Zhang et al.ICCV 2023 · 405 citations
- SparseFusion: Distilling View-Conditioned Diffusion for 3D ReconstructionZhizhuo Zhou, Shubham TulsianiCVPR 2023
- DIRECT-3D: Learning Direct Text-to-3D Generation on Massive Noisy 3D DataQihao Liu, Yi Zhang, Song Bai, Adam Kortylewski et al.CVPR 2024 · 4 citations
