JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation

• URL: http://arxiv.org/abs/2607.26600v1
• Date: Wed, 29 Jul 2026 08:23:46 GMT
• Title: JEPADepth: Masked Predictive Representation Learning for Self-Supervised Monocular Depth Estimation
• Abstract summary: JEPADepth is a self-supervised monocular depth framework that incorporates a complementary training objective.<n>Our method augments a standard photometric pipeline with a masked prediction loss computed in the representation space of a pretrained DINOv3 Vision Transformer encoder.<n>A predictor infers target-region embeddings from visible context-region embeddings under structured masking, and is discarded along with the target encoder at inference time, adding no deployment cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Self-supervised monocular depth estimation typically relies on photometric reconstruction losses that couple depth, pose, and appearance assumptions. In this paper, we propose JEPADepth, a self-supervised monocular depth framework that incorporates a complementary training objective inspired by Image Joint-Embedding Predictive Architectures (I-JEPA) for self-supervised depth learning. Our method augments a standard photometric pipeline with a masked prediction loss computed in the representation space of a pretrained DINOv3 Vision Transformer encoder. A predictor infers target-region embeddings from visible context-region embeddings under structured masking, and is discarded along with the target encoder at inference time, adding no deployment cost. On KITTI, adding the JEPA objective consistently improves performance over the same DINOv3-based photometric baseline, without changing the inference-time architecture. Compared to prior monocular self-supervised methods, JEPADepth is competitive with state-of-the-art transformer-based approaches and outperforms strong CNN-based baselines on the standard benchmark. In zero-shot transfer (trained on KITTI and evaluated without fine-tuning), JEPADepth achieves the best or near-best performance among the compared methods on both Make3D and Cityscapes across multiple metrics.

Related papers

• Large Depth Completion Model from Sparse Observations [28.01552819701954]
  Large Depth Completion Model (LDCM) is a simple, effective, and robust framework for single-view metric depth estimation with sparse observations.<n>LDCM generates metric-accurate dense depth maps using a transformer.
  arXiv  Detail & Related papers  (2026-05-28T15:50:29Z)
• Learning 3D Reconstruction with Priors in Test Time [38.04707926304637]
  We introduce a test-time framework for multiview Transformers (MVTs) that incorporates priors to improve 3D tasks without retraining or modifying pre-trained image-only networks.<n>Our method consistently improves performance over base MVTs by a large margin.
  arXiv  Detail & Related papers  (2026-04-04T22:10:28Z)
• Visual Autoregressive Modelling for Monocular Depth Estimation [69.01449528371916]
  We propose a monocular depth estimation method based on visual autoregressive ( VAR) priors.<n>Our method adapts a large-scale text-to-image VAR model and introduces a scale-wise conditional upsampling mechanism.<n>We report state-of-the-art performance in indoor benchmarks under constrained training conditions, and strong performance when applied to outdoor datasets.
  arXiv  Detail & Related papers  (2025-12-27T17:08:03Z)
• Zero-shot Inexact CAD Model Alignment from a Single Image [53.37898107159792]
  A practical approach to infer 3D scene structure from a single image is to retrieve a closely matching 3D model from a database and align it with the object in the image.<n>Existing methods rely on supervised training with images and pose annotations, which limits them to a narrow set of object categories.<n>We propose a weakly supervised 9-DoF alignment method for inexact 3D models that requires no pose annotations and generalizes to unseen categories.
  arXiv  Detail & Related papers  (2025-07-04T04:46:59Z)
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler [62.06785782635153]
  We propose a new model, UniDepthV2, capable of reconstructing metric 3D scenes from solely single images across domains.<n>UniDepthV2 directly predicts metric 3D points from the input image at inference time without any additional information.<n>Our model exploits a pseudo-spherical output representation, which disentangles the camera and depth representations.
  arXiv  Detail & Related papers  (2025-02-27T14:03:15Z)
• RadOcc: Learning Cross-Modality Occupancy Knowledge through Rendering Assisted Distillation [50.35403070279804]
  3D occupancy prediction is an emerging task that aims to estimate the occupancy states and semantics of 3D scenes using multi-view images. We propose RadOcc, a Rendering assisted distillation paradigm for 3D Occupancy prediction.
  arXiv  Detail & Related papers  (2023-12-19T03:39:56Z)
• FG-Depth: Flow-Guided Unsupervised Monocular Depth Estimation [17.572459787107427]
  We propose a flow distillation loss to replace the typical photometric loss and a prior flow based mask to remove invalid pixels. Our approach achieves state-of-the-art results on both KITTI and NYU-Depth-v2 datasets.
  arXiv  Detail & Related papers  (2023-01-20T04:02:13Z)
• Multi-Frame Self-Supervised Depth with Transformers [33.00363651105475]
  We propose a novel transformer architecture for cost volume generation. We use depth-discretized epipolar sampling to select matching candidates. We refine predictions through a series of self- and cross-attention layers.
  arXiv  Detail & Related papers  (2022-04-15T19:04:57Z)
• Depth-conditioned Dynamic Message Propagation for Monocular 3D Object Detection [86.25022248968908]
  We learn context- and depth-aware feature representation to solve the problem of monocular 3D object detection. We show state-of-the-art results among the monocular-based approaches on the KITTI benchmark dataset.
  arXiv  Detail & Related papers  (2021-03-30T16:20:24Z)
• SynDistNet: Self-Supervised Monocular Fisheye Camera Distance Estimation Synergized with Semantic Segmentation for Autonomous Driving [37.50089104051591]
  State-of-the-art self-supervised learning approaches for monocular depth estimation usually suffer from scale ambiguity. This paper introduces a novel multi-task learning strategy to improve self-supervised monocular distance estimation on fisheye and pinhole camera images.
  arXiv  Detail & Related papers  (2020-08-10T10:52:47Z)
• D3VO: Deep Depth, Deep Pose and Deep Uncertainty for Monocular Visual Odometry [57.5549733585324]
  D3VO is a novel framework for monocular visual odometry that exploits deep networks on three levels -- deep depth, pose and uncertainty estimation. We first propose a novel self-supervised monocular depth estimation network trained on stereo videos without any external supervision. We model the photometric uncertainties of pixels on the input images, which improves the depth estimation accuracy.
  arXiv  Detail & Related papers  (2020-03-02T17:47:13Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.