GiantAI / pixtrack
PixTrack is a Computer Vision method for Object Tracking which uses NeRF templates and feature-metric alignment to robustly track the 6DoF pose of a known object.
☆70Updated last year
Related projects ⓘ
Alternatives and complementary repositories for pixtrack
- [CVPR 2023] "Revisiting Rotation Averaging: Uncertainties and Robust Losses" by Ganlin Zhang, Viktor Larsson and Daniel Barath☆118Updated 7 months ago
- A minimal PyTorch implementation of Bundle Adjustment☆80Updated 10 months ago
- ☆96Updated 7 months ago
- [3DV 2022] GO-Surf: Neural Feature Grid Optimization for Fast, High-Fidelity RGB-D Surface Reconstruction☆162Updated last year
- [CVPR 2023] Two-view Geometry Scoring Without Correspondences☆80Updated last year
- Dense SLAM with an Implicit Neural Representation☆93Updated 2 years ago
- This repository implements our CVPR2022 paper "BNV-Fusion: Dense 3D Reconstruction using Bi-level Neural Volume Fusion"☆135Updated last year
- ☆105Updated last year
- [3DV 2022] The 8-Point Algorithm as an Inductive Bias for Relative Pose Prediction by ViTs☆92Updated last year
- Real-time Neural Representation Fusion for Robust Volumetric Mapping☆129Updated 7 months ago
- COMO: Compact Mapping and Odometry☆173Updated 3 weeks ago
- SLAM-Supported Semi-Supervised Learning for 6D Object Pose Estimation☆73Updated 4 months ago
- ☆55Updated 2 years ago
- A PyTorch re-implementation of iNeRF: Inverting Neural Radiance Fields for Pose Estimation☆33Updated 3 years ago
- The Progressive-X algorithm proposed in paper: Daniel Barath and Jiri Matas; Progressive-X: Efficient, Anytime, Multi-Model Fitting Algor…☆71Updated last year
- [CVPR'21] [Jittor & Pytorch] DI-Fusion: Online Implicit 3D Reconstruction with Deep Priors☆123Updated 2 years ago
- Official code for ObjectMatch: Robust Registration using Canonical Object Correspondences (CVPR 2023)☆37Updated last year
- [CVPR 2024 - Highlight] FAR: Flexible, Accurate and Robust 6DoF Relative Camera Pose Estimation☆111Updated 8 months ago
- ☆50Updated last year
- Code for RelPose (ECCV 2022)☆108Updated last year
- Python scripts and functions to work with COLMAP☆73Updated 4 years ago
- 6DoF Pose Estimation using Neural Radiance Fields☆137Updated 2 years ago
- Benchmarking PyTorch variants of TSDF fusion.☆49Updated 4 years ago
- ☆105Updated last year
- [3DV 2022] Visual Localization via Few-Shot Scene Region Classification.☆30Updated last year
- Code accompanying the paper "Gradient-SDF: A Semi-Implicit Surface Representation for 3D Reconstruction" by Christiane Sommer*, Lu Sang*,…☆69Updated 2 years ago
- Official Implementation of our CVPR 2023 paper: "DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields"☆99Updated last year
- Using adpative feature grid to reduce the memory of NICE-SLAM☆82Updated last year
- SCADE: NeRFs from Space Carving with Ambiguity-Aware Depth Estimates, CVPR 2023☆69Updated last year
- From Correspondences to Pose: Non-minimal Certifiably Optimal Relative Pose without Disambiguation (CVPR 2024 - Highlight)☆54Updated 5 months ago