https://github.com/anshantju/hdes-net
공식 코드Real-Time Monocular Human Depth Estimation and Segmentation on Embedded Systems
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/antabangun/dualrefine
공식 코드https://github.com/antof27/rgb-based-pose-classification
공식 코드https://github.com/anuragranj/cc
공식 코드https://github.com/apple/ml-depth-pro
공식 코드Depth Pro: Sharp Monocular Metric Depth in Less Than a Second
https://github.com/aradhye2002/ecodepth
공식 코드ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation
https://github.com/ardaduz/deep-video-mvs
공식 코드DeepVideoMVS: Multi-View Stereo on Video with Recurrent Spatio-Temporal Fusion
https://github.com/arminmasoumian/gcndepth
공식 코드https://github.com/art-programmer/PlaneNet
공식 코드PlaneNet: Piece-wise Planar Reconstruction from a Single RGB Image
https://github.com/arthurhero/ZbuffDepth
공식 코드Improved Point Transformation Methods For Self-Supervised Depth Prediction
https://github.com/ashutosh1807/depthformer
공식 코드https://github.com/ashutosh1807/pixelformer
공식 코드Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention
https://github.com/astra-vision/SceneRF
공식 코드SceneRF: Self-Supervised Monocular 3D Scene Reconstruction with Radiance Fields
https://github.com/astra-vision/densemtl
공식 코드DenseMTL: Cross-task Attention Mechanism for Dense Multi-task Learning
https://github.com/atapour/temporal-depth-segmentation
공식 코드https://github.com/attackonmuggle/dab_net0
공식 코드Detaching and Boosting: Dual Engine for Scale-Invariant Self-Supervised Monocular Depth Estimation
https://github.com/autonomousvision/unimatch
공식 코드https://github.com/avinashpaliwal/PanoDreamer
공식 코드PanoDreamer: Optimization-Based Single Image to 360 3D Scene With Diffusion
https://github.com/azzarelli/wape
공식 코드https://github.com/baegwangbin/irondepth
공식 코드IronDepth: Iterative Refinement of Single-View Depth using Surface Normal and its Uncertainty
https://github.com/baegwangbin/magnet
공식 코드Multi-View Depth Estimation by Fusing Single-View Depth Probability with Multi-View Geometry
https://github.com/barrybarry-smith/driv3r
공식 코드Driv3R: Learning Dense 4D Reconstruction for Autonomous Driving
https://github.com/baymaxshao/endomust
공식 코드https://github.com/beileicui/endodac
공식 코드https://github.com/beileicui/surgicaldino
공식 코드Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery
https://github.com/beileicui/tr2m
공식 코드https://github.com/bfshi/scaling_on_scales
공식 코드https://github.com/biaslab/depthestimationbnn
공식 코드https://github.com/bionicvisionlab/2021-han-scene-simplification
공식 코드https://github.com/blarklee/monoplflownet
공식 코드https://github.com/bob-cheng/badpart
공식 코드BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
https://github.com/boyagesmile/dna-depth
공식 코드Deep Neighbor Layer Aggregation for Lightweight Self-Supervised Monocular Depth Estimation
https://github.com/br0202/M3Depth
공식 코드Self-Supervised Depth Estimation in Laparoscopic Image using 3D Geometric Consistency
https://github.com/brade31919/radar_depth
공식 코드Depth Estimation from Monocular Images and Sparse Radar Data
https://github.com/brandleyzhou/diffnet
공식 코드Self-Supervised Monocular Depth Estimation with Internal Feature Fusion
https://github.com/brandleyzhou/sub-depth
공식 코드SUB-Depth: Self-distillation and Uncertainty Boosting Self-supervised Monocular Depth Estimation
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.