NeuralLift-360: Lifting an in-the-Wild 2D Photo to A 3D Object with 360° Views
Open accessThe DOI matches its Crossref record; 22 of the 22 references it cites were found in a registry or an index.
Abstract
Virtual reality and augmented reality (XR) bring increasing demand for 3D content generation. However, creating high-quality 3D content requires tedious work from a human expert. In this work, we study the challenging task of lifting a single image to a 3D object and, for the first time, demonstrate the ability to generate a plausible 3D object with 360° views that corresponds well with the given reference image. By conditioning on the reference image, our model can fulfill the everlasting curiosity for synthesizing novel views of objects from images. Our technique sheds light on a promising direction of easing the workflows for 3D artists and XR designers. We propose a novel framework, dubbed NeuralLift-360, that utilizes a depth-aware neural radiance representation (NeRF) and learns to craft the scene guided by denoising diffusion models. By introducing a ranking loss, our NeuralLift-360 can be guided with rough depth estimation in the wild. We also adopt a CLIP-guided sampling strategy for the diffusion prior to provide coherent guidance. Extensive experiments demonstrate that our NeuralLift-360 significantly outperforms existing state-of-the-art baselines. Project page: https://vita-group.github.io/NeuralLift-360/
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
High-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2022) · 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52688.2022.01042 · Cited by 20,302
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
NeRF: representing scenes as neural radiance fields for view synthesis
Mildenhall, B., Srinivasan, P. P., Tancik, M., Barron, J. T., Ramamoorthi, R., & Ng, R. (2022) · Communications of the ACM · doi:10.1145/3503250 · Cited by 6,852
Deep Unsupervised Learning using Nonequilibrium Thermodynamics
Sohl-Dickstein, J., Weiss, E. A., Maheswaranathan, N., & Ganguli, S. (2015) · arXiv · doi:10.48550/arxiv.1503.03585 · Cited by 2,637 · cited 1×
“Given infinitesimal timesteps, the reverse diffusion process can be approximated with Gaussian [56] related with an optimal MSE denoiser [53].”
MethodPhotorealistic Text-to-Image Diffusion Models with Deep Language Understanding
Saharia, C., Chan, W., Saxena, S., Li, L., Whang, J., Denton, E., Ghasemipour, S. K. S., Ayan, B. K., Mahdavi, S. S., Lopes, R. G., et al. (2022) · arXiv · doi:10.48550/arxiv.2205.11487 · Cited by 2,528 · cited 5×
“Modern diffusion models [41,48,50] are trained on a massive dataset (e.”
BackgroundMethodInfluentialHierarchical Text-Conditional Image Generation with CLIP Latents
Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., & Chen, M. (2022) · arXiv · doi:10.48550/arxiv.2204.06125 · Cited by 2,511 · cited 5×
“Modern diffusion models [41,48,50] are trained on a massive dataset (e.”
BackgroundMethodInfluentialDenoising Diffusion Implicit Models
Song, J., Meng, C., & Ermon, S. (2020) · arXiv · doi:10.48550/arxiv.2010.02502 · Cited by 2,507 · cited 1×
“Sampling from a diffusion model can be either stochastic [17] or deterministic [54].”
BackgroundDreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2022) · arXiv · doi:10.48550/arxiv.2208.12242 · Cited by 2,442
Zero-shot text-to-image generation
Ramesh, A., Pavlov, M., Goh, G., Gray, S., Voss, C., Radford, A., Chen, M., & Sutskever, I. (2021) · arXiv · doi:10.48550/arxiv.2102.12092 · Cited by 2,417
Vision Transformers for Dense Prediction
Ranftl, R., Bochkovskiy, A., & Koltun, V. (2021) · 2021 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01196 · Cited by 2,373 · cited 1×
“Under the guidance of monocular depth estimation networks [47, 48], the 2D image is firstly back-projected to a 3D data format (e.”
MethodShapeNet: An Information-Rich 3D Model Repository
Chang, A. X., Funkhouser, T., Guibas, L., Hanrahan, P., Huang, Q., Li, Z., Savarese, S., Savva, M., Song, S., Su, H., et al. (2015) · arXiv · doi:10.48550/arxiv.1512.03012 · Cited by 2,330
DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation
Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., & Aberman, K. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.02155 · Cited by 2,295 · cited 1×
“Adapting to in-the-wild images necessitates finetuning the Stable Diffusion model on the reference image Textual inversion [15] and Dreambooth [49] enable finetuning the Stable Diffusion model on a limited number of images for a subject-driven generation.”
Sigmoid-Weighted Linear Units for Neural Network Function Approximation in Reinforcement Learning
Elfwing, S., Uchibe, E., & Doya, K. (2018) · Neural Networks · doi:10.1016/j.neunet.2017.12.012 · Cited by 2,119
Score-Based Generative Modeling through Stochastic Differential Equations
Song, Y., Sohl-Dickstein, J., Kingma, D. P., Kumar, A., Ermon, S., & Poole, B. (2020) · arXiv · doi:10.48550/arxiv.2011.13456 · Cited by 1,953 · cited 6×
“We also add Gaussian noise to the camera pose sampling phase.”
BackgroundMethodInfluentialGenerative Modeling by Estimating Gradients of the Data Distribution
Song, Y., & Ermon, S. (2019) · arXiv · doi:10.48550/arxiv.1907.05600 · Cited by 1,453 · cited 1×
“Similar to classifier guidance techniques [26, 30, 32, 56], we rewrite pθ(xt|y, z) = pθ(y|xt, z)pθ(xt|z)/pθ(y|z), and we adopt classifier-free guidance to model pθ(xt|z), then we can obtain a modified score function [55] as below:”
MethodHigh-Resolution Image Synthesis with Latent Diffusion Models
Rombach, R., Blattmann, A., Lorenz, D., Esser, P., & Ommer, B. (2021) · arXiv · doi:10.48550/arxiv.2112.10752 · Cited by 737
An Image is Worth One Word: Personalizing Text-to-Image Generation using Textual Inversion
Gal, R., Alaluf, Y., Atzmon, Y., Patashnik, O., Bermano, A. H., Chechik, G., & Cohen-Or, D. (2022) · arXiv · doi:10.48550/arxiv.2208.01618 · Cited by 611
Ordinal Depth Supervision for 3D Human Pose Estimation
Pavlakos, G., Zhou, X., & Daniilidis, K. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00763 · Cited by 486
Kingma, D. P., Salimans, T., Poole, B., & Ho, J. (2021) · arXiv · doi:10.48550/arxiv.2107.00630 · Cited by 374
Monocular Relative Depth Perception with Web Stereo Data Supervision
Xian, K., Shen, C., Cao, Z., Lu, H., Xiao, Y., Li, R., & Luo, Z. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00040 · Cited by 215
Large-scale Text-to-Image Generation Models for Visual Artists’ Creative Works
Ko, H.-K., Park, G., Jeon, H., Jo, J., Kim, J., & Seo, J. (2023) · Proceedings of the 28th International Conference on Intelligent User Interfaces · doi:10.1145/3581641.3584078 · Cited by 189
Web Stereo Video Supervision for Depth Prediction from Dynamic Scenes
Wang, C., Lucey, S., Perazzi, F., & Wang, O. (2019) · 2019 International Conference on 3D Vision (3DV) · doi:10.1109/3dv.2019.00046 · Cited by 103 · cited 1×
“Due to unknown camera baselines and stereoscopic postprocessing in data, these methods [9, 28, 48, 69, 74, 77] utilize loss functions invariant to shift and scale or adopt ranking loss that utilizes relative information.”
Method
Cited by
Zero-1-to-3: Zero-shot One Image to 3D Object
Liu, R., Wu, R., Van Hoorick, B., Tokmakov, P., Zakharov, S., & Vondrick, C. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00853 · Cited by 841
Wonder3D: Single Image to 3D Using Cross-Domain Diffusion
Long, X., Guo, Y.-C., Lin, C., Liu, Y., Dou, Z., Liu, L., Ma, Y., Zhang, S.-H., Habermann, M., Theobalt, C., et al. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.00951 · Cited by 377
SparseNeRF: Distilling Depth Ranking for Few-shot Novel View Synthesis
Wang, G., Chen, Z., Loy, C. C., & Liu, Z. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00832 · Cited by 266
Text2Room: Extracting Textured 3D Meshes from 2D Text-to-Image Models
Höllein, L., Cao, A., Owens, A., Johnson, J., & Nießner, M. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00727 · Cited by 167
Probing the 3D Awareness of Visual Foundation Models
Banani, M. E., Raj, A., Maninis, K.-K., Kar, A., Li, Y., Rubinstein, M., Sun, D., Guibas, L., Johnson, J., & Jampani, V. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.02059 · Cited by 52
“Another line of work combines image generation with 3D representations for text-or image-conditioned 3D reconstruction [62, 88, 93].”
Background
Metadata
- Authors
- Xu, D., Jiang, Y., Wang, P., Fan, Z., Wang, Y., & Wang, Z.
- Venue
- 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2023-06
- Pages
- 4479-4489
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4386066359
- Cited by
- 88
- References
- 22
- FWCI
- 19.26
- Type
- conference paper
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.