Papers with Code 아카이브
Depth Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 10
- 평가표
- 14
- 보존된 평가 기록
- 58
Depth Estimation is the task of measuring the distance of each pixel relative to the camera. Depth is extracted from either monocular (single) or stereo (multiple views of a scene) images. Traditional methods use multi-view geometry to find the relationship between the images. Newer methods can directly estimate depth by minimizing the regression loss, or by learning to generate a novel view from a sequence. The most popular benchmarks are KITTI and NYUv2. Models are typically evaluated according to a RMS metric.
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/needylove/ordinalentropy
공식 코드https://github.com/neurai-lab/cude-monodepthcl
공식 코드Continual Learning of Unsupervised Monocular Depth from Videos
https://github.com/neurai-lab/mimdepth
공식 코드Image Masking for Robust Self-Supervised Monocular Depth Estimation
https://github.com/neurai-lab/mono-pose-attack
공식 코드https://github.com/nianticlabs/depth-hints
공식 코드https://github.com/nianticlabs/implicit-depth
공식 코드https://github.com/nianticlabs/manydepth
공식 코드The Temporal Opportunist: Self-Supervised Multi-Frame Monocular Depth
https://github.com/nianticlabs/map-free-reloc
공식 코드Map-free Visual Relocalization: Metric Pose Relative to a Single Image
https://github.com/nianticlabs/monodepth2
공식 코드https://github.com/nianticlabs/rectified-features
공식 코드https://github.com/nianticlabs/stereo-from-mono
공식 코드https://github.com/nianticlabs/wavelet-monodepth
공식 코드https://github.com/nicolasrosa/Sparse-to-Continuous
공식 코드Sparse-to-Continuous: Enhancing Monocular Depth Estimation using Occupancy Maps
https://github.com/noahzn/ddnd
공식 코드Channel-Aware Distillation Transformer for Depth Estimation on Nano Drones
https://github.com/noahzn/lite-mono
공식 코드https://github.com/nonmy/fdct
공식 코드https://github.com/nopqaq/test3r
공식 코드https://github.com/northsummer/lgkd
공식 코드BEV-LGKD: A Unified LiDAR-Guided Knowledge Distillation Framework for BEV 3D Object Detection
https://github.com/nvidia/torch-harmonics
공식 코드https://github.com/nvlabs/np-cvp-mvsnet
공식 코드Non-parametric Depth Distribution Modelling based Depth Inference for Multi-view Stereo
https://github.com/nvlabs/voxformer
공식 코드VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion
https://github.com/nyu-ce-projects/depth-estimation
공식 코드Self-Supervised Learning based Depth Estimation from Monocular Images
https://github.com/omggggg/mmdg
공식 코드Suppress and Rebalance: Towards Generalized Multi-Modal Face Anti-Spoofing
https://github.com/open-mmlab/mmdetection3d
공식 코드Probabilistic and Geometric Depth: Detecting Objects in Perspective
https://github.com/oppo-us-research/riav-mvs
공식 코드RIAV-MVS: Recurrent-Indexing an Asymmetric Volume for Multi-View Stereo
https://github.com/oucvisiongroup/watermono
공식 코드https://github.com/owen-liuyuxuan/visionfactory
공식 코드Scalable Vision-Based 3D Object Detection and Monocular Depth Estimation for Autonomous Driving
https://github.com/pagraf/MagicBathyNet
공식 코드https://github.com/pagraf/swin-bathyunet
공식 코드https://github.com/pakinwu/vgld
공식 코드VGLD: Visually-Guided Linguistic Disambiguation for Monocular Depth Scale Recovery
https://github.com/pandas-team/autonomous-vehicle-environment-perception
공식 코드An intelligent modular real-time vision-based system for environment perception
https://github.com/pardistaghavi/swinmtl
공식 코드https://github.com/patrickwu2/Depth-Completion
공식 코드Indoor Depth Completion with Boundary Consistency and Self-Attention
https://github.com/patrikperssonmath/MDPN
공식 코드https://github.com/piiswrong/deep3d
공식 코드Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.