https://github.com/dvl-tum/defocus-net
공식 코드Focus on defocus: bridging the synthetic to real domain gap for depth estimation
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/dwhou/emdc-pytorch
공식 코드https://github.com/dylanauty/mde-biological-vision-systems
공식 코드Monocular Depth Estimation Using Cues Inspired by Biological Vision Systems
https://github.com/dylanauty/objcavit
공식 코드https://github.com/ebnerluca/uw_depth
공식 코드Metrically Scaled Monocular Depth Estimation through Sparse Priors for Underwater Robots
https://github.com/eckertzhang/text2nerf
공식 코드Text2NeRF: Text-Driven 3D Scene Generation with Neural Radiance Fields
https://github.com/edadepthmde/edadepth_icmla
공식 코드EDADepth: Enhanced Data Augmentation for Monocular Depth Estimation
https://github.com/edithlzh/VNL_Estimation
공식 코드https://github.com/edm-research/cut-and-splat
공식 코드Cut-and-Splat: Leveraging Gaussian Splatting for Synthetic Data Generation
https://github.com/ehedayati/LFCompressionByRCNN-JPEG
공식 코드https://github.com/ehsanik/SeGAN
공식 코드https://github.com/ehsanik/muscleTorch
공식 코드What Can You Learn from Your Muscles? Learning Visual Representation from Human Interactions
https://github.com/ehzoahis/dered
공식 코드https://github.com/eldar/flash3d
공식 코드Flash3D: Feed-Forward Generalisable 3D Scene Reconstruction from a Single Image
https://github.com/elvintanhust/monocd
공식 코드MonoCD: Monocular 3D Object Detection with Complementary Depths
https://github.com/enisimsar/instance-conv
공식 코드Object-aware Monocular Depth Prediction with Instance Convolutions
https://github.com/ensta-u2is/dido
공식 코드Discretization-Induced Dirichlet Posterior for Robust Uncertainty Quantification on Regression
https://github.com/ensta-u2is/ldu
공식 코드https://github.com/eryixie/planerecnet
공식 코드https://github.com/esandml/ssl4gie
공식 코드A Study on Self-Supervised Pretraining for Vision Problems in Gastrointestinal Endoscopy
https://github.com/explainableml/bayescap
공식 코드BayesCap: Bayesian Identity Cap for Calibrated Uncertainty in Frozen Neural Networks
https://github.com/fabiotosi92/diffusion4robustdepth
공식 코드Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions
https://github.com/fabiotosi92/monoResMatch-Tensorflow
공식 코드Learning monocular depth estimation infusing traditional stereo knowledge
https://github.com/facebookresearch/DistDepth
공식 코드https://github.com/facebookresearch/TemporallyConsistentDepth
공식 코드Temporally Consistent Online Depth Estimation Using Point-Based Fusion
https://github.com/facebookresearch/consistent_depth
공식 코드https://github.com/facebookresearch/dinov2
공식 코드https://github.com/facebookresearch/ijepa
공식 코드Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture
https://github.com/facebookresearch/nerf-det
공식 코드NeRF-Det: Learning Geometry-Aware Volumetric Representation for Multi-View 3D Object Detection
https://github.com/facebookresearch/one_shot_3d_photography
공식 코드https://github.com/facebookresearch/vggt
공식 코드https://github.com/fangchangma/sparse-to-dense
공식 코드Sparse-to-Dense: Depth Prediction from Sparse Depth Samples and a Single Image
https://github.com/fatemehkarimii/lightdepth
공식 코드https://github.com/fcjian/AeDet
공식 코드https://github.com/fcntes/indoordepth
공식 코드Deeper into Self-Supervised Monocular Indoor Depth Estimation
https://github.com/fdarmon/wild_deep_mvs
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.