ishrat-tl Goto Github PK

aot-benchmark

An efficient modular implementation of Associating Objects with Transformers for Video Object Segmentation in PyTorch

ask-anything

[VideoChatGPT] ChatGPT with video understanding! And many more supported LMs such as miniGPT4, StableLM, and MOSS.

autoshot

AutoShot: A Short Video Dataset and State-of-the-Art Shot Boundary Detection - CVPR NAS 2023

consistent_depth

We estimate dense, flicker-free, geometrically consistent depth from monocular video, for example hand-held cell phone video.

detectron2

Detectron2 is a platform for object detection, segmentation and other visual recognition tasks.

e2fgvi

Official code for "Towards An End-to-End Framework for Flow-Guided Video Inpainting" (CVPR2022)

faster-whisper

Faster Whisper transcription with CTranslate2

fastsam

Fast Segment Anything

gcvd-release

groundingdino

Official implementation of the paper "Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection"

lir

Largest Interior/Inscribed Rectangle implementation in Python.

llava

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

medium

math renders for medium articles

mmflow

OpenMMLab optical flow toolbox and benchmark

mmsegmentation

OpenMMLab Semantic Segmentation Toolbox and Benchmark.

monocular-depth-estimation-toolbox

Monocular Depth Estimation Toolbox based on MMSegmentation.

moviechat

🔥 chat with over 10K frames of video!

planarreconstruction

[CVPR'19] Single-Image Piece-wise Planar 3D Reconstruction via Associative Embedding

planerecnet

This is an official implementation for "PlaneRecNet" (BMVC 2021).

recognize-anything

Code for the Recognize Anything Model (RAM) and Tag2Text Model

sceneseg

Codebase for CVPR2020 A Local-to-Global Approach to Multi-modal Movie Scene Segmentation

segment-and-track-anything

An open-source project dedicated to tracking and segmenting any objects in videos, either automatically or interactively. The primary algorithms utilized include the Segment Anything Model (SAM) for key-frame segmentation and Associating Objects with Transformers (AOT) for efficient tracking and propagation purposes.

semantic-segment-anything

Automated dense category annotation engine that serves as the initial semantic labeling for the Segment Anything dataset (SA-1B).

transdepth

Code for Transformers Solve Limited Receptive Field for Monocular Depth Prediction

whisperx

WhisperX: Automatic Speech Recognition with Word-level Timestamps (& Diarization)