paper-with-me

Papers

Monocular Differentiable Rendering for Self-Supervised 3D Object Detection

2020-09-30 · ECCV 2020 8 · Deniz Beker, Hiroharu Kato, Mihai Adrian Morariu, Takahiro Ando, Toru Matsuoka, Wadim Kehl, Adrien Gaidon

3D object detection from monocular images is an ill-posed problem due to the projective entanglement of depth and scale. To overcome this ambiguity, we present a novel self-supervised method for textured 3D shape reconstruction and pose estimation of rigid objects with the help of strong shape priors and 2D instance masks. Our method predicts the 3D location and meshes of each object in an image using differentiable rendering and a self-supervised objective derived from a pretrained monocular depth estimation network. We use the KITTI 3D object detection dataset to evaluate the accuracy of the method. Experiments demonstrate that we can effectively use noisy monocular depth and differentiable rendering as an alternative to expensive 3D ground-truth labels or LiDAR information.

📄 PDF Abstract BibTeX arXiv:2009.14524

Code (0)

등록된 구현이 없습니다.

Tasks

3D Object Detection3D Object Detection From Monocular Images3D Shape ReconstructionDepth EstimationMonocular Depth EstimationObjectobject-detectionObject DetectionPose Estimation

Similar Papers 제목 키워드 기반

Occlusion-Aware Self-Supervised Monocular 6D Object Pose Estimation

2022-03-19 · Gu Wang, Fabian Manhardt, Xingyu Liu, Xiangyang Ji 외

6D object pose estimation is a fundamental yet challenging problem in computer vision. Convolutional Neural Networks (CNNs) have recently proven to be capable of predicting reliable 6D pose estimates even under monocular…

6D Pose Estimation6D Pose Estimation using RGBDomain AdaptationObject+2

CPS++: Improving Class-level 6D Pose and Shape Estimation From Monocular Images With Self-Supervised Learning

2020-03-12 · Fabian Manhardt, Gu Wang, Benjamin Busam, Manuel Nickel 외

Contemporary monocular 6D pose estimation methods can only cope with a handful of object instances. This naturally hampers possible applications as, for instance, robots seamlessly integrated in everyday processes necess…

6D Pose EstimationPose EstimationRetrievalSelf-Supervised Learning

Towards High Fidelity Monocular Face Reconstruction with Rich Reflectance using Self-supervised Learning and Ray Tracing

2021-03-29 · ICCV 2021 10 · Abdallah Dib, Cedric Thebault, Junghyun Ahn, Philippe-Henri Gosselin 외

Robust face reconstruction from monocular image in general lighting conditions is challenging. Methods combining deep neural network encoders with differentiable rendering have opened up the path for very fast monocular …

3D Face ReconstructionFace ReconstructionMonocular ReconstructionSelf-Supervised Learning

MSDA: Monocular Self-supervised Domain Adaptation for 6D Object Pose Estimation

2023-02-14 · Dingding Cai, Janne Heikkilä, Esa Rahtu

Acquiring labeled 6D poses from real images is an expensive and time-consuming task. Though massive amounts of synthetic RGB images are easy to obtain, the models trained on them suffer from noticeable performance degrad…

6D Pose Estimation using RGBDomain AdaptationPose EstimationPseudo Label

SHeaP: Self-Supervised Head Geometry Predictor Learned via 2D Gaussians

2025-04-16 · Liam Schoneveld, Zhe Chen, Davide Davoli, Jiapeng Tang 외

Accurate, real-time 3D reconstruction of human heads from monocular images and videos underlies numerous visual applications. As 3D ground truth data is hard to come by at scale, previous methods have sought to learn fro…

3D ReconstructionEmotion Classification