Composable building blocks to build Llama Apps

ICONIP 2024

A high-quality tool for convert PDF to Markdown and JSON.一站式开源高质量数据提取工具，将PDF转换成Markdown和JSON格式。

Collection of SOTA efficient computer vision models for embedded applications, with pre-trained weights and training recipes

Dead simple FLUX LoRA training UI with LOW VRAM support

Official codes of VEnhancer: Generative Space-Time Enhancement for Video Generation

Deep Height Decoupling for Precise Vision-based 3D Occupancy Prediction

Official PyTorch Implementation of Scribble-Guided Diffusion

LED : Light Enhanced Depth Estimation at Night

SimCMF: A Simple Cross-modal Fine-tuning Strategy from Vision Foundation Models to Any Imaging Modality

Official implementation of ImprovingText-guided ObjectInpainting with SemanticPre-inpainting in ECCV 2024

[ECCV2024] FlashSplat: 2D to 3D Gaussian Splatting Segmentation Solved Optimally

Code for "Accelerating Training with Neuron Interaction and Nowcasting Networks"

LITE: A Paradigm Shift: Multi Object Tracking with Deep Association Metric

The official implementation of MpoxMamba.

[AAAI2025] UniDet3D: Multi-dataset Indoor 3D Object Detection

[ACMMM 2024] Hybrid Cost Volume for Memory-Efficient Optical Flow

RCNet: Deep Recurrent Collaborative Network for Multi-View Low-Light Image Enhancement

Public repository for the ECCV 2024 paper "Train Till You Drop: Towards Stable and Robust Source-free Unsupervised 3D Domain Adaptation".