paper-with-me

Papers

Residual-Guided Learning Representation for Self-Supervised Monocular Depth Estimation

2021-11-08 · Byeongjun Park, Taekyung Kim, Hyojun Go, Changick Kim

Photometric consistency loss is one of the representative objective functions commonly used for self-supervised monocular depth estimation. However, this loss often causes unstable depth predictions in textureless or occluded regions due to incorrect guidance. Recent self-supervised learning approaches tackle this issue by utilizing feature representations explicitly learned from auto-encoders, expecting better discriminability than the input image. Despite the use of auto-encoded features, we observe that the method does not embed features as discriminative as auto-encoded features. In this paper, we propose residual guidance loss that enables the depth estimation network to embed the discriminative feature by transferring the discriminability of auto-encoded features. We conducted experiments on the KITTI benchmark and verified our method's superiority and orthogonality on other state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2111.04310

Code (0)

등록된 구현이 없습니다.

Tasks

Depth EstimationMonocular Depth EstimationSelf-Supervised Learning

Similar Papers 제목 키워드 기반

Semantically-Guided Representation Learning for Self-Supervised Monocular Depth

2020-02-27 · ICLR 2020 1 · Vitor Guizilini, Rui Hou, Jie Li, Rares Ambrus 외

Self-supervised learning is showing great promise for monocular depth estimation, using geometry as the only source of supervision. Depth networks are indeed capable of learning representations that relate visual appeara…

Depth EstimationDepth PredictionMonocular Depth EstimationRepresentation Learning+2

Fine-grained Semantics-aware Representation Enhancement for Self-supervised Monocular Depth Estimation

2021-08-19 · ICCV 2021 10 · Hyunyoung Jung, Eunhyeok Park, Sungjoo Yoo

Self-supervised monocular depth estimation has been widely studied, owing to its practical importance and recent promising improvements. However, most works suffer from limited supervision of photometric consistency, esp…

Depth EstimationMetric LearningMonocular Depth Estimation

JacobianAvatar: Temporally Consistent Semi-rigid Avatar Reconstruction from a Monocular Video

2026-06-30 · Changyeon Won, Min-Gyu Park, Seonghwan Park, Ju Hong Yoon 외 arxiv

Generating realistic human avatars in complex motions--such as clothing dynamics--requires modeling of global and local deformations which remains challenging in monocular settings. We address this problem by leveraging …

Self-supervised Dense 3D Reconstruction from Monocular Endoscopic Video

2019-09-06 · Xingtong Liu, Ayushi Sinha, Masaru Ishii, Gregory D. Hager 외

We present a self-supervised learning-based pipeline for dense 3D reconstruction from full-length monocular endoscopic videos without a priori modeling of anatomy or shading. Our method only relies on unlabeled monocular…

3D ReconstructionAnatomySelf-Supervised Learning

Towards Comprehensive Representation Enhancement in Semantics-guided Self-supervised Monocular Depth Estimation

2022-10-23 · ECCV 2022 10 · Jingyuan Ma, Xiangyu Lei, Nan Liu, Xian Zhao 외

Semantics-guided self-supervised monocular depth estimation has been widely researched, owing to the strong cross-task correlation of depth and semantics. However, since depth estimation and semantic segmentation are fu…

Depth EstimationMetric LearningMonocular Depth EstimationSemantic Segmentation+1