Ganlin Zhang

[3DV 2026] ViSTA-SLAM: Visual SLAM with Symmetric Two-view Association

GlORIE-SLAM: Globally Optimized RGB-only Implicit Encoding Point Cloud SLAM

[CVPR 2023] "Revisiting Rotation Averaging: Uncertainties and Robust Losses" by Ganlin Zhang, Viktor Larsson and Daniel Barath

Using adpative feature grid to reduce the memory of NICE-SLAM

Course project of Advanced Systems Lab 2022 in ETH Zurich.

No description.

BA-T is a research project from TU Munich and ETH Zurich introducing a transformer-based method that refines camera positions and 3D point locations from pairs of photos. No code is available yet, readers should consult the accompanying arXiv paper.

Improved-PSMNet: Combining PSM, group-wise corr, dilatedResNet, segmentation to estimate accurate disparity of stereo image pairs efficiently.

No description.

EECS126 final project. Using Poisson Process to simulate traffic

A feed-forward 3D foundation model for reconstructing scenes from streaming data

An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.

MapAnything: Universal Feed-Forward Metric 3D Reconstruction

This is the repo of EECS C106A project, RoboArt.

Python wrapper for DBoW3. Research purpose.

Official implementation of Continuous 3D Perception Model with Persistent State

Docker for LSD-SLAM, with ubuntu 18.04

iTechX: Open source, edX-style, free course sharing platform.

No description.

My personal solutions of problems in Algorithm Lab 2021HS in ETHZ.

Implementation of modified Brent Method

Computer Architecture project2, ShanghaiTech