[AAAI 2024] BEV-MAE: Bird's Eye View Masked Autoencoders for Point Cloud Pre-training in Autonomous Driving Scenarios

Mix3D: Out-of-Context Data Augmentation for 3D Scenes (3DV 2021 Oral)

This repository contains the implementation for the paper "Revisiting Few Shot Object Detection with Vision-Language Models"

A minimal web-UI for talking to Ollama (and OpenAI) servers

Official repository for the NuScenes-MQA. This paper is accepted by LLVA-AD Workshop at WACV 2024.

An easy way to apply LoRA to CLIP. Implementation of the paper "Low-Rank Few-Shot Adaptation of Vision-Language Models" (CLIP-LoRA) [CVPRW 2024].

This is official code about "Out-of-Distribution Detection with Prototypical Outlier Proxy" in AAAI 2025

YOLO-UniOW: Efficient Universal Open-World Object Detection

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. C…

OpenAD: Open-World Autonomous Driving Benchmark for 3D Object Detection

Building One-class Detector for Anything: Open-vocabulary Zero-shot OOD Detection UsingText-image Models

Training a network on the mnist_dataset in tensorflow and then deploying it in C++.

[ECCV2024] The Official Implementation for ''AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection''

[ECCV 2024] DriveDreamer: Towards Real-world-driven World Models for Autonomous Driving

[ECCV 2024] LabelDistill: Label-guided Cross-modal Knowledge Distillation for Camera-based 3D Object Detection

Data and code for ECCV2024 paper "CMD: A Cross Mechanism Domain Adaptation Dataset for 3D Object Detection".

Re-editable LaTeX/ typst graphics for Inkscape

CapDec: SOTA Zero Shot Image Captioning Using CLIP and GPT2, EMNLP 2022 (findings)

Code base of the BEVDet series .

Official PyTorch implementation of the paper ‘VLM2Scene: Self-Supervised Image-Text-LiDAR Learning with Foundation Models for Autonomous Driving Scene Understanding’ (AAAI'2024)

Official implementation of the paper “MagicDrive3D: Controllable 3D Generation for Any-View Rendering in Street Scenes”

[ICLR24] Official implementation of the paper “MagicDrive: Street View Generation with Diverse 3D Geometry Control”

The PyTorch implementation for "DEAL: Disentangle and Localize Concept-level Explanations for VLMs" (ECCV 2024 Strong Double Blind)

[ECCV 2024 - Oral Presentation] Python library that provides tools for calibrating object detectors and evaluating them

[CVPR 2024] Exploring Orthogonality in Open World Object Detection

Implementation of the paper "Learning to Prompt CLIP for Monocular Depth Estimation: Exploring the Limits of Human Language", ICCV Workshop on Open Vocabulary Scene Understanding (OpenSUN3D) 2023