Lune

AAAI2020Top-tier venue

Synthetic Depth Transfer for Monocular 3D Object Pose Estimation in the Wild

Yueying Kao, Weiming Li, Qiang Wang, Zhouchen Lin, Wooshik Kim, Sunghoon Hong

Abstract

Monocular object pose estimation is an important yet challenging computer vision problem. Depth features can provide useful information for pose estimation. However, existing methods rely on real depth images to extract depth features, leading to its difficulty on various applications. In this paper, we aim at extracting RGB and depth features from a single RGB image with the help of synthetic RGB-depth image pairs for object pose estimation. Specifically, a deep convolutional neural network is proposed with an RGB-to-Depth Embedding module and a Synthetic-Real Adaptation module. The embedding module is trained with synthetic pair data to learn a depth-oriented embedding space between RGB and depth images optimized for object pose estimation. The adaptation module is to further align distributions from synthetic to real data. Compared to existing methods, our method does not need any real depth images and can be trained easily with large-scale synthetic data. Extensive experiments and comparisons show that our method achieves best performance on a challenging public PASCAL 3D+ dataset in all the metrics, which substantiates the superiority of our method and the above modules.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Related papers

  1. Pseudo Flow Consistency for Self-Supervised 6D Object Pose EstimationYang Hai, Rui Song, Jiaojiao Li, David Ferstl et al.ICCV 2023 · 13 citations
  2. Cross-Domain 3D Hand Pose Estimation with Dual ModalitiesQiuxia Lin, Linlin Yang, Angela YaoCVPR 2023
  3. Is Depth Really Necessary for Salient Object Detection?Jiawei Zhao, Yifan Zhao, Jia Li, Xiaowu ChenACM MM 2020 · 71 citations
  4. Unified Category-Level Object Detection and Pose Estimation from RGB Images Using 3D PrototypesTom Fischer, Xiaojie Zhang, Eddy IlgICCV 2025 · 2 citations
  5. SynDeMo: Synergistic Deep Feature Alignment for Joint Learning of Depth and Ego-MotionBehzad Bozorgtabar, Mohammad Saeed Rad, Dwarikanath Mahapatra, Jean-Philippe ThiranICCV 2019 · 44 citations
Dusk over the sea between two cliffs drawn in fine vertical lines