Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains

• URL: http://arxiv.org/abs/2303.07662v3
• Date: Mon, 15 Apr 2024 08:37:57 GMT
• Title: Do More With What You Have: Transferring Depth-Scale from Labeled to Unlabeled Domains
• Authors: Alexandra Dana, Nadav Carmel, Amit Shomer, Ofer Manela, Tomer Peleg,
• Abstract summary: Self-supervised depth estimators result in up-to-scale predictions that are linearly correlated to their absolute depth values across the domain. We show that aligning the field-of-view of two datasets prior to training results in a common linear relationship for both domains. We use this observed property to transfer the depth-scale from source datasets that have absolute depth labels to new target datasets that lack these measurements.
• Score: 43.16293941978469
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Transferring the absolute depth prediction capabilities of an estimator to a new domain is a task with significant real-world applications. This task is specifically challenging when images from the new domain are collected without ground-truth depth measurements, and possibly with sensors of different intrinsics. To overcome such limitations, a recent zero-shot solution was trained on an extensive training dataset and encoded the various camera intrinsics. Other solutions generated synthetic data with depth labels that matched the intrinsics of the new target data to enable depth-scale transfer between the domains. In this work we present an alternative solution that can utilize any existing synthetic or real dataset, that has a small number of images annotated with ground truth depth labels. Specifically, we show that self-supervised depth estimators result in up-to-scale predictions that are linearly correlated to their absolute depth values across the domain, a property that we model in this work using a single scalar. In addition, aligning the field-of-view of two datasets prior to training, results in a common linear relationship for both domains. We use this observed property to transfer the depth-scale from source datasets that have absolute depth labels to new target datasets that lack these measurements, enabling absolute depth predictions in the target domain. The suggested method was successfully demonstrated on the KITTI, DDAD and nuScenes datasets, while using other existing real or synthetic source datasets, that have a different field-of-view, other image style or structural content, achieving comparable or better accuracy than other existing methods that do not use target ground-truth depths.

Related papers

• MICDrop: Masking Image and Depth Features via Complementary Dropout for Domain-Adaptive Semantic Segmentation [155.0797148367653]
  Unsupervised Domain Adaptation (UDA) is the task of bridging the domain gap between a labeled source domain and an unlabeled target domain. We propose to leverage geometric information, i.e., depth predictions, as depth discontinuities often coincide with segmentation boundaries. We show that our method can be plugged into various recent UDA methods and consistently improve results across standard UDA benchmarks.
  arXiv  Detail & Related papers  (2024-08-29T12:15:10Z)
• Compositional Semantic Mix for Domain Adaptation in Point Cloud Segmentation [65.78246406460305]
  compositional semantic mixing represents the first unsupervised domain adaptation technique for point cloud segmentation. We present a two-branch symmetric network architecture capable of concurrently processing point clouds from a source domain (e.g. synthetic) and point clouds from a target domain (e.g. real-world)
  arXiv  Detail & Related papers  (2023-08-28T14:43:36Z)
• Knowledge Combination to Learn Rotated Detection Without Rotated Annotation [53.439096583978504]
  Rotated bounding boxes drastically reduce output ambiguity of elongated objects. Despite the effectiveness, rotated detectors are not widely employed. We propose a framework that allows the model to predict precise rotated boxes.
  arXiv  Detail & Related papers  (2023-04-05T03:07:36Z)
• 3D-PL: Domain Adaptive Depth Estimation with 3D-aware Pseudo-Labeling [37.315964084413174]
  We develop a domain adaptation framework via generating reliable pseudo ground truths of depth from real data to provide direct supervisions. Specifically, we propose two mechanisms for pseudo-labeling: 1) 2D-based pseudo-labels via measuring the consistency of depth predictions when images are with the same content but different styles; 2) 3D-aware pseudo-labels via a point cloud completion network that learns to complete the depth values in the 3D space.
  arXiv  Detail & Related papers  (2022-09-19T17:54:17Z)
• Ranking Distance Calibration for Cross-Domain Few-Shot Learning [91.22458739205766]
  Recent progress in few-shot learning promotes a more realistic cross-domain setting. Due to the domain gap and disjoint label spaces between source and target datasets, their shared knowledge is extremely limited. We employ a re-ranking process for calibrating a target distance matrix by discovering the reciprocal k-nearest neighbours within the task.
  arXiv  Detail & Related papers  (2021-12-01T03:36:58Z)
• Domain Adaptation for Real-World Single View 3D Reconstruction [1.611271868398988]
  unsupervised domain adaptation can be used to transfer knowledge from the labeled synthetic source domain to the unlabeled real target domain. We propose a novel architecture which takes advantage of the fact that in this setting, target domain data is unsupervised with regards to the 3D model but supervised for class labels. Results are performed with ShapeNet as the source domain and domains within the Object Domain Suite (ODDS) dataset as the target.
  arXiv  Detail & Related papers  (2021-08-24T22:02:27Z)
• Domain Adaptive Monocular Depth Estimation With Semantic Information [13.387521845596149]
  We propose an adversarial training model that leverages semantic information to narrow the domain gap. The proposed compact model achieves state-of-the-art performance comparable to complex latest models.
  arXiv  Detail & Related papers  (2021-04-12T18:50:41Z)
• Flexible deep transfer learning by separate feature embeddings and manifold alignment [0.0]
  Object recognition is a key enabler across industry and defense. Unfortunately, algorithms trained on existing labeled datasets do not directly generalize to new data because the data distributions do not match. We propose a novel deep learning framework that overcomes this limitation by learning separate feature extractions for each domain.
  arXiv  Detail & Related papers  (2020-12-22T19:24:44Z)
• Unsupervised Metric Relocalization Using Transform Consistency Loss [66.19479868638925]
  Training networks to perform metric relocalization traditionally requires accurate image correspondences. We propose a self-supervised solution, which exploits a key insight: localizing a query image within a map should yield the same absolute pose, regardless of the reference image used for registration. We evaluate our framework on synthetic and real-world data, showing our approach outperforms other supervised methods when a limited amount of ground-truth information is available.
  arXiv  Detail & Related papers  (2020-11-01T19:24:27Z)
• Synthetic-to-Real Domain Adaptation for Lane Detection [5.811502603310248]
  We explore learning from abundant, randomly generated synthetic data, together with unlabeled or partially labeled target domain data. This poses the challenge of adapting models learned on the unrealistic synthetic domain to real images. We develop a novel autoencoder-based approach that uses synthetic labels unaligned with particular images for adapting to target domain data.
  arXiv  Detail & Related papers  (2020-07-08T10:54:21Z)

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.