xuheny

sam-hq

Segment Anything in High Quality [NeurIPS 2023]

dust3r

DUSt3R: Geometric 3D Vision Made Easy

FlowMDM

[CVPR 2024] Official Implementation of "Seamless Human Motion Composition with Blended Positional Encodings".

tofu

Official code for ICCV 2021 oral paper: Topologically Consistent Multi-View Face Inference Using Volumetric Sampling

PhaseBetweener

Creating animation sequences between sparse key frames using motion phase features.

AI4Animation

Bringing Characters to Life with Computer Brains in Unity

ganimator

A motion generation model learned from a single example [SIGGRAPH 2022]

Style-Transfer-for-Headshot-Portraits

Python implementation of YiChang Shih's "Style Transfer for Headshots Portraits" [http://www.connellybarnes.com/work/publications/2014_portrait.pdf]

EMO

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

segment-anything

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

sam-pt

SAM-PT: Extending SAM to zero-shot video segmentation with point-based tracking.

Awesome-Video-Object-Segmentation

A curated list of video object segmentation (vos) papers, datasets, and projects.

SimVOS

Painter

Painter & SegGPT Series: Vision Foundation Models from BAAI

DiffusionLight

[CVPR 2024] code release for "DiffusionLight: Light Probes for Free by Painting a Chrome Ball"

vis2vos

Converting VIS json label to VOS format

RoHM

The official PyTorch code for RoHM: Robust Human Motion Reconstruction via Diffusion.

UniRef

[ICCV2023] Segment Every Reference Object in Spatial and Temporal Spaces

TrackGPT

Tracking with Human-Intent Reasoning

slahmr

GLoT

Global-to-Local Modeling for Video-based 3D Human Pose and Shape Estimation

Cutie

[CVPR 2024 Highlight] Putting the Object Back Into Video Object Segmentation

XMem2

A tool for efficient semi-supervised video object segmentation (great results with minimal manual labor) and a dataset for benchmarking

XMem

[ECCV 2022] XMem: Long-Term Video Object Segmentation with an Atkinson-Shiffrin Memory Model

dot

Dense Optical Tracking: Connecting the Dots

Tracking-Anything-with-DEVA

[ICCV 2023] Tracking Anything with Decoupled Video Segmentation

WHAM

MotionBERT

[ICCV 2023] PyTorch Implementation of "MotionBERT: A Unified Perspective on Learning Human Motion Representations"

VIBE

Official implementation of CVPR2020 paper "VIBE: Video Inference for Human Body Pose and Shape Estimation"

DL-HPE