Rex Cheng

MMAudio. [CVPR 2025] MMAudio: Taming Multimodal Joint Training for High-Quality Video-to-Audio Synthesis

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

Tracking-Anything-with-DEVA. [ICCV 2023] Tracking Anything with Decoupled Video Segmentation

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

CascadePSP. [CVPR 2020] CascadePSP: Toward Class-Agnostic and Very High-Resolution Segmentation via Global and Local Refinement

STCN. [NeurIPS 2021] Rethinking Space-Time Networks with Improved Memory Coverage for Efficient Video Object Segmentation

MiVOS. [CVPR 2021] Modular Interactive Video Object Segmentation: Interaction-to-Mask, Propagation and Difference-Aware Fusion. Semi-supervised VOS as well!

Mask-Propagation. [CVPR 2021] MiVOS - Mask Propagation module. Reproduced STM (and better) with training code :star2:. Semi-supervised video object segmentation evaluation.

Scribble-to-Mask. [CVPR 2021] MiVOS - Scribble to Mask module

av-benchmark. Benchmarking for Audio-Text and Audio-Visual Generation; Supports FAD, FD_VGG, FD_PANNs, FD_PaSST, IS_PaSST, IS_PANNs, KL_PaSST, KL_PANNs, LAION-CLAP, MS-CLAP, DeSync

Grounded-Segment-Anything. Grounded-SAM: Marrying Grounding DINO with Segment Anything & Stable Diffusion & Recognize Anything - Automatically Detect , Segment and Generate Anything

vos-benchmark. Fast and general video object segmentation evaluation.

C2OT. [ICCV 2025] The Curse of Conditions: Analyzing and Improving Optimal Transport for Conditional Flow-Based Generation

Weighted_Softmax_Loss. Weighted Softmax Loss Layer for Caffe

PyTorch-ARCNN. A test script for ARCNN powered by PyTorch.

nitrous-ema. Fast and simple post-hoc EMA (Karras et al., 2023) for PyTorch with minimal `.item()` calls. ~78% lower overhead than ema_pytorch.

davis2016-evaluation. Python

shared-memory-tensor-dataset. This repository provides an example of reading from a single shared memory tensor from multiple processes (e.g., with DDP).

STM. Video Object Segmentation using Space-Time Memory Networks

Course-Data-Analyser. A project for COMP2021 which analyse data of courses in HKUST

CharTrans-GAN. Use GAN to perform style transfer of Chinese characters.

BlenderVOSRenderer. Python

kinetics_to_frames. Convert kinetics datasets (or other video datasets) to frames. Support resizing and temporal sampling for space efficiency.

ema-pytorch. A simple way to keep track of an Exponential Moving Average (EMA) version of your pytorch model

pysc2. StarCraft II Learning Environment

Android-Matrix-Calculator. A simple android matrix calculator which supports input of unknowns.

imm_2018. Code for unsupervised learning of object landmarks as proposed in "Unsupervised Learning of Object Landmarks through Conditional Image Generation", Tomas Jakab*, Ankush Gupta*, Hakan Bilen, Andrea Vedaldi, Advances in Neural Information Processing Systems (NeurIPS) 2018.

pysc2-rl-agents. StarCraft II / PySC2 Deep Reinforcement Learning Agents (A2C)

htyc-eitc-student. This is a repo for storing and sharing the resources provided to EITC students in HTYC.

pytorch-semseg. Semantic Segmentation Architectures Implemented in PyTorch

Markov-Next-Word. A next-word prediction program using Markov chain with n-gram written in Go.

VisualChat-Painter-example. Java

darknet. Convolutional Neural Networks

DeepGrabCut-PyTorch. Deep GrabCut in PyTorch

so. Stackoverflow answers

ImageBind. ImageBind One Embedding Space to Bind Them All