Visual Autoregressive Modelling for Monocular Depth Estimation
Not on the map. Why?
Abstract (arXiv)
We propose a monocular depth estimation method based on visual autoregressive (VAR) priors, offering an alternative to diffusion-based approaches. Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism with classifier-free guidance. Our approach performs inference in ten fixed autoregressive stages, requiring only 74K synthetic samples for fine-tuning, and achieves competitive results. We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets. This work establishes autoregressive priors as a complementary family of geometry-aware generative models for depth estimation, highlighting advantages in data scalability, and adaptability to 3D vision tasks. Code available at "https://github.com/AmirMaEl/VAR-Depth".
Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 56 of its 63 references that are in the map. First posted on arXiv 27 Dec 2025.
Builds on
56 of 63 references.
References · 56
- 2014Adam: A Method for Stochastic Optimizationcited by 36,960
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
- 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
- 2019Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformercited by 14,491
- 2023LLaMA: Open and Efficient Foundation Language Modelscited by 13,958
- 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,764
- 2022Classifier-Free Diffusion Guidancecited by 5,717
- 2017Neural Discrete Representation Learningcited by 4,650
- 2023Mamba: Linear-Time Sequence Modeling with Selective State Spacescited by 4,616
- 2022LAION-5B: An open large-scale dataset for training next generation image-text modelscited by 4,131
- 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
- 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
38 more
- 2019CutMix: Regularization Strategy to Train Strong Classifiers with Localizable Featurescited by 2,875
- 2021Vision Transformers for Dense Predictioncited by 1,789
- 2021LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairscited by 1,544
- 2019Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfercited by 1,484
- 2024Depth Anything V2cited by 1,385
- 2019Generating Diverse High-Fidelity Images with VQ-VAE-2cited by 1,376
- 2022Scaling Autoregressive Models for Content-Rich Text-to-Image Generationcited by 1,287
- 2014Depth Map Prediction from a Single Image using a Multi-Scale Deep Networkcited by 1,264
- 2022MaskGIT: Masked Generative Image Transformercited by 1,082
- 2024Visual Autoregressive Modeling: Scalable Image Generation via Next-Scale Predictioncited by 1,005
- 2016Conditional Image Generation with PixelCNN Decoderscited by 859
- 2023Vision-Language Models for Vision Tasks: A Surveycited by 834
- 2016Unsupervised Monocular Depth Estimation with Left-Right Consistencycited by 819
- 2017Unsupervised Learning of Depth and Ego-Motion from Videocited by 778
- 2024Autoregressive Model Beats Diffusion: Llama for Scalable Image Generationcited by 760
- 2022Autoregressive Image Generation using Residual Quantizationcited by 706
- 2023Muse: Text-To-Image Generation via Masked Generative Transformerscited by 640
- 2023Language Model Beats Diffusion -- Tokenizer is Key to Visual Generationcited by 633
- 2020AdaBins: Depth Estimation using Adaptive Binscited by 596
- 2020Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understandingcited by 593
- 2016Deeper Depth Prediction with Fully Convolutional Residual Networkscited by 402
- 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 389
- 2016Unsupervised CNN for Single View Depth Estimation: Geometry to the Rescuecited by 368
- 2018GeoNet: Unsupervised Learning of Dense Depth, Optical Flow and Camera Posecited by 341
- 2016Virtual Worlds as Proxy for Multi-Object Tracking Analysiscited by 340
- 2021Omnidata: A Scalable Pipeline for Making Multi-Task Mid-Level Vision Datasets from 3D Scanscited by 336
- 2023Repurposing Diffusion-Based Image Generators for Monocular Depth Estimationcited by 323
- 2024Infinity: Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesiscited by 297
- 2024GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Imagecited by 283
- 2019DIODE: A Dense Indoor and Outdoor DEpth Datasetcited by 236
- 2015Learning Depth from Single Monocular Images Using Deep Convolutional Neural Fieldscited by 169
- 2024Lumina-mGPT: Illuminate Flexible Photorealistic Text-to-Image Generation with Multimodal Generative Pretrainingcited by 148
- 2023The Surprising Effectiveness of Diffusion Models for Optical Flow and Monocular Depth Estimationcited by 116
- 2017Occlusion Aware Unsupervised Learning of Optical Flowcited by 101
- 2023Monocular Depth Estimation using Diffusion Modelscited by 87
- 2024Fine-Tuning Image-Conditional Diffusion Models is Easier than You Thinkcited by 82
- 2025Marigold: Affordable Adaptation of Diffusion-Based Image Generators for Image Analysiscited by 78
- 2018AdaDepth: Unsupervised Content Congruent Adaptation for Depth Estimationcited by 54
50 most cited of 56 All 56 (JSON)
Built on by
Citing papers per year: 2026: 2.
2 papers.