Recurrent Switching Linear Dynamical Systems

High-Resolution Image Synthesis with Latent Diffusion Models

[ICRA'23] DytanVO: Visual Odometry in Dynamic Environments

TartanVO: A Generalizable Learning-based VO

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

PyTorch implementation of the U-Net for image semantic segmentation with high quality images

Open3D: A Modern Library for 3D Data Processing

This is the official PyTorch implementation of the CVPR 2020 paper "TransMoMo: Invariance-Driven Unsupervised Video Motion Retargeting".

Motion Retargeting Video Subjects

Source code for the paper "Quasi-Newton Solver for Robust Non-Rigid Registration" (CVPR2020 Oral).

Point Cloud Library (PCL)

Opt DSL

Deformation Loop Closure sample code to enable non-rigid alignment of point clouds

Convert any Triangle Mesh to Watertight Manifold

a module for 3D semantic segmentation in point clouds.

Code used in the research project CAD-Deform: Deformable Fitting of CAD Models to 3D Scans