Enforcing Temporal Consistency in Video Depth Estimation, ICCV-W 2021.

Research Platform for Image-Guided Therapy

pySLAM contains a monocular Visual Odometry (VO) pipeline in Python. It supports many modern local features based on Deep Learning.

Set-of-Mark Prompting for LMMs

PPSNet: Leveraging Near-Field Lighting for Monocular Depth Estimation from Endoscopy Videos (ECCV, 2024)

[CVPR 2024 Highlight] Official PyTorch implementation of SpatialTracker: Tracking Any 2D Pixels in 3D Space

Class activation maps for your PyTorch models (CAM, Grad-CAM, Grad-CAM++, Smooth Grad-CAM++, Score-CAM, SS-CAM, IS-CAM, XGrad-CAM, Layer-CAM)

Joint deep network for feature line detection and description

This is an official implementation for "Bidirectional Semi-supervised Dual-branch CNN for Robust 3D Reconstruction of Stereo Endoscopic Images via Adaptive Cross and Parallel Supervisions".

[IPCAI'2024 (IJCARS special issue)] Surgical-DINO: Adapter Learning of Foundation Models for Depth Estimation in Endoscopic Surgery

Python optical flow visualization following Baker et al. (ICCV 2007) as used by the MPI-Sintel challenge

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

Deformable visual odometry for stereo endoscopic videos

Dense Optical Tracking: Connecting the Dots

ParticleSfM: Exploiting Dense Point Trajectories for Localizing Moving Cameras in the Wild. ECCV 2022.

Analysis of MFSF (multi-frame subspace constrained optic flow) tracking of Hydra

GLPDepth PyTorch Implementation: Global-Local Path Networks for Monocular Depth Estimation with Vertical CutDepth

This is a set of MATLAB and Python functions for visualization and plotting of continuum robots.

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

[PAMI 2022, CVPR 2023] ASH: Parallel Spatial Hashing for Fast Scene Reconstruction

SplaTAM: Splat, Track & Map 3D Gaussians for Dense RGB-D SLAM (CVPR 2024)

PositionBasedDynamics is a library for the physically-based simulation of rigid bodies, deformable solids and fluids.

Object-wise Non-Rigid Structure-from-Motion with a Topological Template

A C++ Library for Monocular Real-Time 3D Shape Tracking of Isometrically Deforming Objects