[CVPR 2024] Neural Markov Random Field for Stereo Matching

🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.

🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.

Official implementation of AAAI 2023 paper "Parameter-efficient Model Adaptation for Vision Transformers"

A collection of parameter-efficient transfer learning papers focusing on computer vision and multimodal domains.

The Paper List of Large Multi-Modality Model, Parameter-Efficient Finetuning, Vision-Language Pretraining, Conventional Image-Text Matching for Preliminary Insight.

A curated list of prompt-based paper in computer vision and vision-language learning.

[TPAMI] Searching prompt modules for parameter-efficient transfer learning.

A Unified Library for Parameter-Efficient and Modular Transfer Learning

Low rank adaptation for Vision Transformer

Code for loralib, an implementation of "LoRA: Low-Rank Adaptation of Large Language Models"

❄️🔥 Visual Prompt Tuning [ECCV 2022] https://arxiv.org/abs/2203.12119

[RA-L 2024] Fieldscale: Locality-Aware Field-based Adaptive Rescaling for Thermal Infrared Image

AnyLoc: Universal Visual Place Recognition (RA-L 2023)

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

[ICRA'23] BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

[CoRL'23] Parting with Misconceptions about Learning-based Vehicle Motion Planning

[ECCV 2024] Official implementation of the paper "Semantic-SAM: Segment and Recognize Anything at Any Granularity"

An Open-Ended Embodied Agent with Large Language Models

Repository of DELIVER dataset and CMNeXt models (CVPR 2023)

This is the official GitHub page of the Multi-Spectral Stereo (MS2) dataset described in CVPR 2023 paper.

Python tools for working with KITTI data.

Code for ICLR2021 paper "Robust and Generalizable Visual Representation Learning via Random Convolutions"

[CVPR 2023] Multi-frame depth estimation in dynamic scenes. -- Li, Rui, et al. "Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes".

A toolbox for mapping and localization with line features.