cvlab-kaist / locotrack
Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)
☆135Updated last week
Related projects ⓘ
Alternatives and complementary repositories for locotrack
- [ECCV 2024] Improving 2D Feature Representations by 3D-Aware Fine-Tuning☆229Updated 2 weeks ago
- [ECCV 2024] Decomposition Betters Tracking Everything Everywhere☆111Updated 4 months ago
- ☆81Updated 2 months ago
- Official implementation of "Diffusion Model for Dense Matching" (ICLR'24 Oral)☆151Updated 4 months ago
- ☆91Updated 2 months ago
- MFT: Long-Term Tracking of Every Pixel -- code for the WACV 2024 paper☆50Updated 5 months ago
- Official Code For Track Everything Everywhere Fast and Robustly☆45Updated 2 months ago
- [ACCV 2024 (Oral)] Official Implementation of "Moving Object Segmentation: All You Need Is SAM (and Flow)" Junyu Xie, Charig Yang, Weidi …☆272Updated 2 weeks ago
- ChronoDepth: Learning Temporally Consistent Video Depth from Video Diffusion Priors☆192Updated 4 months ago
- [CVPR2024] SANeRF-HQ: Segment Anything for NeRF in High Quality.☆41Updated 4 months ago
- Official code implementation of "DäRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation"(NeurIPS 2023)☆65Updated 8 months ago
- Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)☆127Updated 3 weeks ago
- [CVPR'2024] Official implementation of the paper "ECoDepth: Effective Conditioning of Diffusion Models for Monocular Depth Estimation"☆164Updated last month
- GenPercept: Diffusion Models Trained with Large Data Are Transferable Visual Models☆125Updated 2 weeks ago
- Official Implementation of "PF3plat: Pose-Free Feed-Forward 3D Gaussian Splatting"☆127Updated last week
- Source code for CVPR 2024 paper UnSAMFlow Unsupervised Optical Flow Guided by Segment Anything Model.☆76Updated 6 months ago
- Official PyTorch implementation of Self-Supervised Any-Point Tracking by Contrastive Random Walks, ECCV 2024.☆42Updated last week
- [ICCV2023] 🧊FrozenRecon: Pose-free 3D Scene Reconstruction with Frozen Depth Models☆118Updated 2 months ago
- Official Implementation of paper "Telling Left from Right: Identifying Geometry-Aware Semantic Correspondence"☆95Updated this week
- Official implementation of Flash3D paper☆119Updated 3 months ago
- run DROID-SLAM with Metric3D to improve monocular performance☆101Updated last month
- ID-Pose: Sparse-view Camera Pose Estimation by Inverting Diffusion Models☆123Updated 6 months ago
- ☆90Updated last week
- [ECCV 2024] Pytorch code for our ECCV'24 paper NeRF-MAE: Masked AutoEncoders for Self-Supervised 3D Representation Learning for Neural Ra…☆81Updated 3 months ago
- ☆117Updated 5 months ago
- [ECCV 2024] Leveraging Synthetic Data for Real-Domain High-Resolution Monocular Metric Depth Estimation☆33Updated last month
- Code for our CVPR 2023 paper on online, temporally consistent depth estimation.☆91Updated last year
- ☆69Updated last year
- [ECCV 2024] Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions☆70Updated last month