mkocabas
Follow
Lists (1)
Stars
ReLoo: Reconstructing Humans Dressed in Loose Garments from Monocular Video in the Wild (ECCV2024)
Code to easily try 30 (and growing) different image matching methods
iBOT 🤖: Image BERT Pre-Training with Online Tokenizer (ICLR 2022)
This is official implementation of the paper: "iHuman: Instant Animatable Digital Humans From Monocular Videos" [ECCV 2024]
The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery 🧑🔬
Fine-Tuning Image-Conditional Diffusion Models is Easier than You Think
GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)
Code for "GVHMR: World-Grounded Human Motion Recovery via Gravity-View Coordinates", Siggraph Asia 2024
Official Repository for ECCV 2024 paper Beyond the Contact: Discovering Comprehensive Affordance for 3D Objects from Pre-trained 2D Diffusion Models
Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.
StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text
Official repository for Splatt3R: Zero-shot Gaussian Splatting from Uncalibrated Image Pairs
Various AI scripts. Mostly Stable Diffusion stuff.
An extremely fast Python package and project manager, written in Rust.
High-resolution models for human tasks.
PyTorch code and pretrained weights for the UNIC models.
On-device Inference of Diffusion Models for Apple Silicon
VILA - a multi-image visual language model with training, inference and evaluation recipe, deployable from cloud to edge (Jetson Orin and laptops)
RTMPose series (RTMPose, DWPose, RTMO, RTMW) without mmcv, mmpose, mmdet etc.
Python inverse kinematics based on Pinocchio