markkua

markkua's Stars

• NVIDIA/Cosmos

  Cosmos is a world model development platform that consists of world foundation models, tokenizers and video processing pipeline to accelerate the development of Physical AI at Robotics & AV labs. Cosmos is purpose built for physical AI. The Cosmos repository will enable end users to run the Cosmos models, run inference scripts and generate videos.

  Language:Python7.5k473

• SysCV/shift-dev

  SHIFT Dataset DevKit - CVPR2022

  Language:Python10410

• DepthAnything/Video-Depth-Anything

  Video Depth Anything: Consistent Depth Estimation for Super-Long Videos

  Language:Python59936

• Tencent/Hunyuan3D-2

  High-Resolution 3D Assets Generation with Large Scale Hunyuan3D Diffusion Models.

  Language:Python6.2k463

• genmoai/mochi

  The best OSS video generation models

  Language:Python2.9k303

• lucidrains/local-attention

  An implementation of local windowed attention for language modeling

  Language:Python41543

• NVIDIA/Cosmos-Tokenizer

  A suite of image and video neural tokenizers

  Language:Jupyter Notebook1.6k68

• prs-eth/Marigold-DC

  Zero-Shot Monocular Depth Completion with Guided Diffusion

  Language:Python1226

• princeton-vl/DROID-SLAM

  Language:Python1.9k309

• microsoft/TRELLIS

  Official repo for paper "Structured 3D Latents for Scalable and Versatile 3D Generation".

  Language:Python7.7k558

• prs-eth/RollingDepth

  Video Depth without Video Models

  Language:Python44516

• prs-eth/ukraine-damage-mapping-tool

  An Open-Source Tool for Mapping War Destruction at Scale in Ukraine using Sentinel-1 Time Series

  Language:Jupyter Notebook11

• PyAV-Org/PyAV

  Pythonic bindings for FFmpeg's libraries.

  Language:Cython2.7k378

• kkroening/ffmpeg-python

  Python bindings for FFmpeg - with complex filtering support

  Language:Python10.3k899

• SunYangtian/Splatter_A_Video

  [NeurIPS 2024] Official code for "Splatter a Video: Video Gaussian Representation for Versatile Processing"

  Language:Python120

• y-zheng18/point_odyssey

  Official code for PointOdyssey: A Large-Scale Synthetic Dataset for Long-Term Point Tracking (ICCV 2023)

  Language:Python1377

• apple/ml-depth-pro

  Depth Pro: Sharp Monocular Metric Depth in Less Than a Second.

  Language:Python4.1k297

• naver/mast3r

  Grounding Image Matching in 3D with MASt3R

  Language:Python1.7k133

• VisualComputingInstitute/diffusion-e2e-ft

  [WACV 2025] Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think

  Language:Python38710

• facebookresearch/dynamic_stereo

  [CVPR 2023] DynamicStereo: Consistent Dynamic Depth from Stereo Videos.

  Language:Jupyter Notebook1959

• jimmycv07/DiffIR2VR-Zero

  Language:Python14012

• Tencent/DepthCrafter

  DepthCrafter: Generating Consistent Long Depth Sequences for Open-world Videos

  Language:Python1.2k64

• HKBU-HPML/IRS

  IRS: A Large Synthetic Indoor Robotics Stereo Dataset for Disparity and Surface Normal Estimation

  Language:Python12015

• osmr/propainter

  Streaming ProPainter

  Language:Python13

• Chen-Rao/VD-Diff

  Official implementation of Paper "Rethinking Video Deblurring with Wavelet-Aware Dynamic Transformer and Diffusion Model" (ECCV 2024)

  Language:Python13

• Jack-bo1220/Awesome-Remote-Sensing-Foundation-Models

  1.1k102

• Vinayak-VG/GAURA

  Language:Python61

• Dao-AILab/flash-attention

  Fast and memory-efficient exact attention

  Language:Python15.5k1.5k

• 360CVGroup/FancyVideo

  This is the official reproduction of FancyVideo.

  Language:Python72472

• basilevh/gcd

  Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation

  Language:Python2215