The DOI matches its Crossref record; 13 of the 13 references it cites were found in a registry or an index.
Autoregressive Image Generation using Residual Quantization
Open accessAbstract
For autoregressive (AR) modeling of high-resolution images, vector quantization (VQ) represents an image as a sequence of discrete codes. A short sequence length is important for an AR model to reduce its computational costs to consider long-range interactions of codes. However, we postulate that previous VQ cannot shorten the code sequence and generate high-fidelity images together in terms of the rate-distortion trade-off. In this study, we propose the two-stage framework, which consists of Residual-Quantized VAE (RQ-VAE) and RQ-Transformer, to effectively generate high-resolution images. Given a fixed codebook size, RQ-VAE can precisely approximate a feature map of an image and represent the image as a stacked map of discrete codes. Then, RQ-Transformer learns to predict the quantized feature vector at the next position by predicting the next stack of codes. Thanks to the precise approximation of RQ-VAE, we can represent a$256\times 256$image as$8\times 8$resolution of the feature map, and RQ-Transformer can efficiently reduce the computational costs. Consequently, our framework out-performs the existing AR models on various benchmarks of unconditional and conditional image generation. Our approach also has a significantly faster sampling speed than previous AR models to generate high-quality images.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Discrete visual tokenizers additionally involve a quantizer (Lee et al., 2022; Mentzer et al., 2023; van den Oord et al., 2017; Yu et al., 2024,; Zhao et al., 2024) that further discretizes the continuous latents into a discrete space, allowing for easy integration into large language models (LLMs) and vision language models (VLMs) alongside other modalities, such as text and audio.”
From Cosmos World Foundation Model Platform for Physical AI (2025) · cites this paper as Lee et al., 2022
Experimental — accuracy not yet measured
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
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
ImageNet: A large-scale hierarchical image database
Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., & Fei-Fei, L. (2009) · 2009 IEEE Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2009.5206848 · Cited by 65,333
Language Models are Few-Shot Learners
Brown, T. B., Mann, B., Ryder, N., Subbiah, M., Kaplan, J., Dhariwal, P., Neelakantan, A., Shyam, P., Sastry, G., Askell, A., et al. (2020) · arXiv · doi:10.48550/arxiv.2005.14165 · Cited by 23,372
Image-to-Image Translation with Conditional Adversarial Networks
Isola, P., Zhu, J.-Y., Zhou, T., & Efros, A. A. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.632 · Cited by 22,930
Learning Transferable Visual Models From Natural Language Supervision
Radford, A., Kim, J. W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et al. (2021) · arXiv · doi:10.48550/arxiv.2103.00020 · Cited by 15,293
Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network
Ledig, C., Theis, L., Huszar, F., Caballero, J., Cunningham, A., Acosta, A., Aitken, A., Tejani, A., Totz, J., Wang, Z., et al. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.19 · Cited by 12,696
A Style-Based Generator Architecture for Generative Adversarial Networks
Karras, T., Laine, S., & Aila, T. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00453 · Cited by 11,714
Transformers: State-of-the-Art Natural Language Processing
Wolf, T., Debut, L., Sanh, V., Chaumond, J., Delangue, C., Moi, A., Cistac, P., Rault, T., Louf, R., Funtowicz, M., et al. (2020) · Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: System Demonstrations · doi:10.18653/v1/2020.emnlp-demos.6 · Cited by 8,741
Denoising Diffusion Probabilistic Models
Ho, J., Jain, A., & Abbeel, P. (2020) · arXiv · doi:10.48550/arxiv.2006.11239 · Cited by 8,712
GANs Trained by a Two Time-Scale Update Rule Converge to a Local Nash Equilibrium
Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., & Hochreiter, S. (2017) · arXiv · doi:10.48550/arxiv.1706.08500 · Cited by 8,365
Large Scale GAN Training for High Fidelity Natural Image Synthesis
Brock, A., Donahue, J., & Simonyan, K. (2018) · arXiv · doi:10.48550/arxiv.1809.11096 · Cited by 3,717
Diffusion Models Beat GANs on Image Synthesis
Dhariwal, P., & Nichol, A. (2021) · arXiv · doi:10.48550/arxiv.2105.05233 · Cited by 3,362
Conceptual Captions: A Cleaned, Hypernymed, Image Alt-text Dataset For Automatic Image Captioning
Sharma, P., Ding, N., Goodman, S., & Soricut, R. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1238 · Cited by 1,879
Research works printed but not linked: 30
- shannon, 1959, Coding theorems for a discrete source with a fidelity criterion, IRE Nat Conv Rec, 4, 1
- ramesh, 2021, Zero-shot text-to-image generation, Proceedings of the 38th International Conference on Machine Learning volume 139 of Proceedings of Machine Learning Research, 8821
- van den oord, 0, Conditional image generation with pixelcnn decoders, Proceedings of the 30th International Conference on Neural Information Processing Systems, 4797
- van oord, 0, Pixel recurrent neural networks, Proceedings of the 33rd International Conference on Machine Learning
- 10.18653/v1/P16-1162 · DOI · Paper page
- salimans, 0, Kingma. Pixelcnn++: A pixelcnn implementation with discretized logistic mixture likelihood and other modifications, ICLRE
- razavi, 0, Generating diverse high-fidelity images with vq-vae-2, Advances in neural information processing systems, 14866
- ranzato, 2016, Sequence level training with recurrent neural networks, 4th International Conference on Learning Representations ICLR 2016
- dosovitskiy, 2020, An image is worth 16×16 words: Transformers for image recognition at scale, ArXiv Preprint
- van den oord, 2017, Neural discrete representation learning, Advances in neural information processing systems, 30
- esser, 2021, Imagebart Bidirectional context with multi-nomial diffusion for autoregressive image synthesis
- 10.1109/CVPR46437.2021.01268 · DOI · Paper page
- ferdowsi, 2017, Regularized residual quantization: a multi-layer sparse dictionary learning approach, ArXiv Preprint
- goodfellow, 2014, Generative adversarial nets, Advances in neural information processing systems, 27
- 10.1016/B978-0-08-051584-7.50011-5 · DOI · Paper page
- henighan, 2020, Scaling laws for autoregressive generative modeling, ArXiv Preprint
- martinez, 2014, Stacked quantizers for compositional vector compression, ArXiv Preprint
- 10.1109/ICCV.2017.282 · DOI
- 10.1016/0004-3702(90)90060-D · DOI
- nash, 2021, Generating images with sparse representations, Proceedings of the 38th International Conference on Machine Learning volume 139 of Proceedings of Machine Learning Research, 7958
- chen, 0, Generative pretraining from pixels, International Conference on Machine Learning, 1691
- dhariwal, 2020, Jukebox: A generative model for music, ArXiv Preprint
- bengio, 2015, Scheduled sampling for sequence prediction with recurrent neural networks, ArXiv Preprint
- 10.1109/CVPR.2014.124 · DOI
- 10.1109/ICASSP.1982.1171604 · DOI
- johnson, 0, Perceptual losses for real-time style transfer and super-resolution, European Conference on Computer Vision, 694
- 10.1109/CVPR42600.2020.00813 · DOI · Paper page
- vaswani, 0, Attention is all you need, Advances in neural information processing systems, 5998
- 10.1609/aaai.v35i10.17036 · DOI
- yu, 2015, Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop, ArXiv Preprint
Cited by
Sorted by citations
Adapting Large Language Models by Integrating Collaborative Semantics for Recommendation
Zheng, B., Hou, Y., Lu, H., Chen, Y., Zhao, W. X., Chen, M., & Wen, J.-R. (2024) · 2024 IEEE 40th International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00118 · Cited by 143
Diffusion Models, Image Super-Resolution, and Everything: A Survey
Moser, B. B., Shanbhag, A. S., Raue, F., Frolov, S., Palacio, S., & Dengel, A. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3476671 · Cited by 117
Muse: Text-To-Image Generation via Masked Generative Transformers
Chang, H., Zhang, H., Barber, J., Maschinot, A., Lezama, J., Jiang, L., Yang, M.-H., Murphy, K., Freeman, W. T., Rubinstein, M., et al. (2023) · arXiv · doi:10.48550/arxiv.2301.00704 · Cited by 157
Cosmos World Foundation Model Platform for Physical AI
NVIDIA, :, Agarwal, N., Ali, A., Bala, M., Balaji, Y., Barker, E., Cai, T., Chattopadhyay, P., Chen, Y., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.03575 · Cited by 13
Self-citation
Metadata
- Authors
- Lee, D., Kim, C., Kim, S., Cho, M., & Han, W.-S.
- Affiliations
- Pohang University of Science and Technology (KR)
- Kakao Brain (South Korea) (KR)
- Venue
- 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- Publisher
- IEEE
- Published
- 2022-06
- Pages
- 11513-11522
- ISSN
- 1063-6919 (ISSN-L)
- OpenAlex
- W4312974539
- Cited by
- 445
- References
- 13
- Citations by year
- 2026: 224 · 2025: 138 · 2024: 50 · 2023: 31 · 2022: 2
- FWCI
- 18.19
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Funders
- Ministry of Science and ICT, South Korea
- Institute for Information and Communications Technology Promotion (2021-0-00537)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Data Compression Techniques
- Keywords
- autoregressive image generation, vector quantization, residual quantization, high-resolution image generation, rate-distortion tradeoff, codebook, computational efficiency, conditional image generation, unconditional image generation, sampling speed
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
