https://github.com/feihuzhang/GANet
공식 코드GA-Net: Guided Aggregation Net for End-to-end Stereo Matching
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/feixh/GeoSup
공식 코드https://github.com/fengyi233/SCIPaD
공식 코드SCIPaD: Incorporating Spatial Clues into Unsupervised Pose-Depth Joint Learning
https://github.com/fengyi233/ViPOcc
공식 코드https://github.com/fengziyue/FusionDepth
공식 코드Advancing Self-supervised Monocular Depth Learning with Sparse LiDAR
https://github.com/fkluger/cuboids_revisited
공식 코드https://github.com/freeformrobotics/lifelong-monodepth
공식 코드Lifelong-MonoDepth: Lifelong Learning for Multi-Domain Monocular Metric Depth Estimation
https://github.com/fubel/synthehicle
공식 코드Synthehicle: Multi-Vehicle Multi-Camera Tracking in Virtual Cities
https://github.com/fudan-zvg/ego3rt
공식 코드https://github.com/fudan-zvg/meta-prompts
공식 코드Harnessing Diffusion Models for Visual Perception with Meta Prompts
https://github.com/fuenwang/LED2-Net
공식 코드LED2-Net: Monocular 360 Layout Estimation via Differentiable Depth Rendering
https://github.com/fuenwang/bifusev2
공식 코드BiFuse++: Self-supervised and Efficient Bi-projection Fusion for 360 Depth Estimation
https://github.com/fwucas/fa-depth
공식 코드FA-Depth: Toward Fast and Accurate Self-supervised Monocular Depth Estimation
https://github.com/fwucas/hqdec
공식 코드HQDec: Self-Supervised Monocular Depth Estimation Based on a High-Quality Decoder
https://github.com/galaxies99/transcg
공식 코드https://github.com/gallenszl/ucfnet
공식 코드Digging Into Uncertainty-based Pseudo-label for Robust Stereo Matching
https://github.com/gandolfczjh/3d2fool
공식 코드Physical 3D Adversarial Attacks against Monocular Depth Estimation in Autonomous Driving
https://github.com/gangweix/acvnet
공식 코드Attention Concatenation Volume for Accurate and Efficient Stereo Matching
https://github.com/gangweix/igev
공식 코드https://github.com/ganwanshui/simpleoccupancy
공식 코드A Simple Framework for 3D Occupancy Estimation in Autonomous Driving
https://github.com/geo-tell/ds-pmnet
공식 코드Learning Deformable Hypothesis Sampling for Accurate PatchMatch Multi-View Stereo
https://github.com/gitkaichenzhou/devnet
공식 코드DevNet: Self-supervised Monocular Depth Learning via Density Volume Construction
https://github.com/gojasper/lbm
공식 코드LBM: Latent Bridge Matching for Fast Image-to-Image Translation
https://github.com/gongxinyao/robust-photon-efficient-imaging-using-prsnet
공식 코드Robust photon-efficient imaging using a pixel-wise residual shrinkage network
https://github.com/google-research-datasets/2.5vrd
공식 코드https://github.com/google-research/big_vision
공식 코드UViM: A Unified Modeling Approach for Vision with Learned Guiding Codes
https://github.com/google-research/deeplab2
공식 코드https://github.com/google-research/google-research
공식 코드HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
https://github.com/google-research/google-research/tree/master/dual_pixels
공식 코드https://github.com/google-research/google-research/tree/master/hitnet
공식 코드HITNet: Hierarchical Iterative Tile Refinement Network for Real-time Stereo Matching
https://github.com/google-research/google-research/tree/master/robust_loss
공식 코드https://github.com/griffbr/tfod
공식 코드https://github.com/gruberto/PixelAccurateDepthBenchmark
공식 코드Pixel-Accurate Depth Evaluation in Realistic Driving Scenarios
https://github.com/gtzly/FADNet
공식 코드Monocular 3D Object Detection with Sequential Feature Association and Depth Hint Augmentation
https://github.com/guangmingw/DOPlearning
공식 코드Unsupervised Learning of Depth, Optical Flow and Pose with Occlusion from 3D Geometry
https://github.com/guoleisun/indiscernible-object-counting
공식 코드출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.