Code for ICCV'2025 "RayZer: A Self-supervised Large View Synthesis Model"

An unified model for 4D human-scene reconstruction

NVIDIA Isaac Sim™ is an open-source application on NVIDIA Omniverse for developing, simulating, and testing AI-driven robots in realistic virtual environments.

Awesome work on object 6 DoF pose estimation

A Rao-Blackwellized Particle Filter for 6D Object Pose Tracking

[ECCV 2022] PillarNet: Real-Time and High-Performance Pillar-based 3D Object Detection

Fast mesh to 3D gaussian splat conversion

Ultralytics YOLO 🚀

Glowbuzzer tools

An educational AI robot based on NVIDIA Jetson Nano.

ILIAS: Instance-Level Image retrieval At Scale

Normalizing Flows for Human Pose Anomaly Detection [ICCV 2023]

Code for training adversarial patches that suppress YOLO’s person detections. Includes patch generation, optimization with Top-K anchor selection, smoothness regularization (TV loss), evaluation on…

Online Ray Tracing Tool | 光线追踪

Repository sharing code and the model for the paper "Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixes"

Lip2Vec

[NeurIPS'24 Oral] Official repository for the paper "Scale Equivariant Graph Metanetworks"

TripoSR: Fast 3D Object Reconstruction from a Single Image

[SIGGRAPH'24] A Construct-Optimize Approach to Sparse View Synthesis without Camera Pose

A monitor of resources, forked for GPU support - merged into btop!

Framework for Easily Invertible Architectures

Conditional Generative model (Normalizing Flow) and experimenting style transfer using this model

Implementation of normalizing flows compatible with Bijectors.jl

PyTorch3D is FAIR's library of reusable components for deep learning with 3D data

The Persistence of Vision Raytracer (POV-Ray)

The official implementation of paper "ColorFlow: Retrieval-Augmented Image Sequence Colorization". ColorFlow：基于检索增强的图像序列上色