https://github.com/avinashpaliwal/MaskDnGAN
공식 코드Multi-Stage Raw Video Denoising with Adversarial Loss and Gradient Mask
Papers with Code 아카이브
Optical Flow Estimation
태스크의 하위 분류와 논문·코드·평가·기법·데이터셋을 탐색하세요.
- 하위 태스크
- 1
- 평가표
- 10
- 보존된 평가 기록
- 133
Optical Flow Estimation is a computer vision task that involves computing the motion of objects in an image or a video sequence. The goal of optical flow estimation is to determine the movement of pixels or features in the image, which can be used for various applications such as object tracking, motion analysis, and video compression.
Approaches for optical flow estimation include correlation-based, block-matching, feature tracking, energy-based, and more recently gradient-based.
Further readings:
Definition source: Devon: Deformable Volume Network for Learning Optical Flow
Image credit: Optical Flow Estimation
코드
관련 논문과 평가 결과에 연결된 구현입니다. 출처에서 확인된 저자 구현에는 공식 코드 표시가 있습니다.
https://github.com/avirambh/ScopeFlow
공식 코드https://github.com/bachzz/wflow-tartanvo
공식 코드https://github.com/baidu-research/UnDepthflow
공식 코드Joint Unsupervised Learning of Optical Flow and Depth by Watching Stereo Videos
https://github.com/baowenbo/DAIN
공식 코드https://github.com/baurst/liso
공식 코드https://github.com/baymaxshao/endomust
공식 코드https://github.com/berk-github/OF_interp
공식 코드An Optical Flow-Based Approach for Minimally-Divergent Velocimetry Data Interpolation
https://github.com/berkerdemirel/decompl
공식 코드https://github.com/bigai-nlco/lstp-chat
공식 코드Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
https://github.com/bigai-nlco/videotgb
공식 코드Efficient Temporal Extrapolation of Multimodal Large Language Models with Temporal Grounding Bridge
https://github.com/bob-cheng/badpart
공식 코드BadPart: Unified Black-box Adversarial Patch Attacks against Pixel-wise Regression Tasks
https://github.com/boneddeng/tadml
공식 코드https://github.com/booturbo/hmaflow
공식 코드HMAFlow: Learning More Accurate Optical Flow via Hierarchical Motion Field Alignment
https://github.com/bowenl0218/mmvc_video_codec
공식 코드https://github.com/bradleybin/locate-globally-segment-locally-a-progressive-architecture-with-knowledge-review-network-for-sod
공식 코드Learning Video Salient Object Detection Progressively from Unlabeled Videos
https://github.com/bryanyzhu/Hidden-Two-Stream
공식 코드Hidden Two-Stream Convolutional Networks for Action Recognition
https://github.com/bytedance/particle-sfm
공식 코드ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild
https://github.com/callsys/flowtext
공식 코드FlowText: Synthesizing Realistic Scene Text Video with Optical Flow Estimation
https://github.com/caojiezhang/VSR-Transformer
공식 코드https://github.com/cartucho/surgt_benchmarking
공식 코드SurgT challenge: Benchmark of Soft-Tissue Trackers for Robotic Surgery
https://github.com/centreborelli/L1BSR
공식 코드https://github.com/chan8972/Spike-FlowNet
공식 코드Spike-FlowNet: Event-based Optical Flow Estimation with Energy-Efficient Hybrid Neural Networks
https://github.com/changhaonan/mono-star-demo
공식 코드Mono-STAR: Mono-camera Scene-level Tracking and Reconstruction
https://github.com/charlesnchr/vsr-sim
공식 코드Spatio-temporal Vision Transformer for Super-resolution Microscopy
https://github.com/chen-du/De-fencing
공식 코드Accurate and efficient video de-fencing using convolutional neural networks and temporal information
https://github.com/chenxuluo/EPC
공식 코드Every Pixel Counts ++: Joint Learning of Geometry and Motion with 3D Holistic Understanding
https://github.com/codepointer/tidenet
공식 코드TIDE: Temporally Incremental Disparity Estimation via Pattern Flow in Structured Light System
https://github.com/codnjsqkr/FastAno_official
공식 코드FastAno: Fast Anomaly Detection via Spatio-temporal Patch Transformation
https://github.com/computational-ocularscience/sstm
공식 코드SSTM: Spatiotemporal Recurrent Transformers for Multi-frame Optical Flow Estimation
https://github.com/connectedsystemslab/batmobility_ae
공식 코드BatMobility: Towards Flying Without Seeing for Autonomous Drones
https://github.com/coolbeam/UPFlow_pytorch
공식 코드UPFlow: Upsampling Pyramid for Unsupervised Optical Flow Learning
https://github.com/csbhr/CDVD-TSP
공식 코드Cascaded Deep Video Deblurring Using Temporal Sharpness Prior
https://github.com/csbhr/self-blind-vsr
공식 코드https://github.com/cszhilu1998/raw-to-srgb
공식 코드Learning RAW-to-sRGB Mappings with Inaccurately Aligned Supervision
https://github.com/cszhilu1998/selfdzsr
공식 코드Self-Supervised Learning for Real-World Super-Resolution from Dual and Multiple Zoomed Observations
출처: Papers with Code · CC BY-SA 4.0. 아카이브 자료와 새로 수집한 논문은 별도로 관리합니다.