facebookresearch / UnSAMFlowLinks
Source code for CVPR 2024 paper UnSAMFlow Unsupervised Optical Flow Guided by Segment Anything Model.
☆107Updated last year
Alternatives and similar repositories for UnSAMFlow
Users that are interested in UnSAMFlow are comparing it to the libraries listed below
Sorting:
- [ECCV 2024] Mono-ViFI: A Unified Learning Framework for Self-supervised Single- and Multi-frame Monocular Depth Estimation☆49Updated 7 months ago
- FlowFormer++: Masked Cost Volume Autoencoding for Pretraining Optical Flow Estimation☆176Updated last year
- Official Code of "[ICCV 2023] MPI-Flow: Learning Realistic Optical Flow with Multiplane Images"☆62Updated last year
- PyTorch implementation of GAFlow: Incorporating Gaussian Attention into Optical Flow (ICCV-2023)☆42Updated last year
- [IJCV 2024] SplatFlow: Learning Multi-frame Optical Flow via Splatting☆59Updated 4 months ago
- [ECCV 2024] LayeredFlow: A Real-World Benchmark for Non-Lambertian Multi-Layer Optical Flow☆42Updated 9 months ago
- [ECCV 2024] Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions☆92Updated last year
- [CVPR 2024] MemFlow: Optical Flow Estimation and Prediction with Memory☆205Updated 6 months ago
- [ICCV2023 Oral & TPAMI2024] NDDepth: Normal-Distance Assisted Monocular Depth Estimation and Completion☆128Updated 9 months ago
- [ICCV 2023] ELFNet: Evidential Local-global Fusion for Stereo Matching☆48Updated last year
- [ICCV 2025 Highlight] BridgeDepth: Bridging Monocular and Stereo Reasoning with Latent Alignment☆81Updated last month
- Official implementation of "Diffusion Model for Dense Matching" (ICLR'24 Oral)☆184Updated last year
- [ECCV 2024] ProDepth: Boosting Self-Supervised Multi-Frame Monocular Depth with Probabilistic Fusion☆35Updated 8 months ago
- [CVPR'24] Robust Synthetic-to-Real Transfer for Stereo Matching☆53Updated last year
- Official implementation of our paper "Flow-Anything: Learning Real-World Optical Flow Estimation from Large-Scale Single-view Images"☆65Updated 3 months ago
- Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)☆194Updated 5 months ago
- A repository of AAAI 2024 paper 'SAMFlow: Eliminating Any Fragmentation in Optical Flow with Segment Anything Model'☆16Updated last year
- [CVPR 2023] Rethinking Optical Flow from Geometric Matching Consistent Perspective☆99Updated 2 years ago
- MFT: Long-Term Tracking of Every Pixel -- code for the WACV 2024 paper☆62Updated 10 months ago
- Unofficial pytorch implementation of DDVM.☆86Updated 10 months ago
- [CVPR2023] This is an official implementation for "PlaneDepth: Self-supervised Depth Estimation via Orthogonal Planes".☆107Updated 2 years ago
- A new baseline and benchmark for robust monocular depth estimation☆23Updated 7 months ago
- Official implementation of "WorDepth: Variational Language Prior for Monocular Depth Estimation"☆41Updated 8 months ago
- Muggled DPT: Depth estimation without the magic☆105Updated 2 weeks ago
- The official implementation of “Segment Anything Model is a Good Teacher for Local Feature Learning”.☆119Updated 3 months ago
- PrimeDepth: Efficient Monocular Depth Estimation with a Stable Diffusion Preimage☆50Updated 4 months ago
- [NeurIPS2023] IEBins: Iterative Elastic Bins for Monocular Depth Estimation☆89Updated 9 months ago
- Official PyTorch implementation of Self-Supervised Any-Point Tracking by Contrastive Random Walks, ECCV 2024.☆53Updated 11 months ago
- ViTA: Video Transformer Adaptor for Robust Video Depth Estimation☆47Updated last year
- code for ScaleFlow++☆41Updated 9 months ago