DeepPhysicVision

AC-Net

Attention-Visualization

Visualization for simple attention and Google's multi-head attention.

Awesome-BEV-Detection-Performance

Collect the Performance of 3D Object Detection Methods from Multi-View Camera Images (BEV Perception).

Awesome-Papers-World-Models-Autonomous-Driving

Awesome Papers about World Models in Autonomous Driving

Awesome-Transformer-Attention

An ultimately comprehensive paper list of Vision Transformer/Attention, including papers, codes, and related websites

Awesome-World-Model

Collect some World Models for Autonomous Driving papers.

deep_complex_networks

Implementation related to the Deep Complex Networks

ECA-Mixer

Code for Fast physic-informed mixer architecture for color Lensfree holographic reconstruction (ECA-Mixer)

EF-Net

Targeted aspect based multimodal sentiment analysis:an attention capsule extraction and multi-head fusion network

ScatterNet

Code for all work presented in Nanophotonic Particle Simulation and Inverse Design Using Artificial Neural Networks

DeepPhysicVision/ECA-Mixer

Code for Fast physic-informed mixer architecture for color Lensfree holographic reconstruction (ECA-Mixer)

DeepPhysicVision/Awesome-Papers-World-Models-Autonomous-Driving

Awesome Papers about World Models in Autonomous Driving

DeepPhysicVision/Awesome-World-Model

Collect some World Models for Autonomous Driving papers.

DeepPhysicVision/Collaborative_Perception

This repository is a paper digest of recent advances in collaborative / cooperative / multi-agent perception for V2I / V2V / V2X autonomous driving scenario.

DeepPhysicVision/BEV-Perception

Bird's Eye View Perception

DeepPhysicVision/BEVFusionMIT

BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representation

DeepPhysicVision/BEVHeight

An official code release of our CVPR'23 paper, BEVHeight

DeepPhysicVision/CoBEVFlow

[NeurIPS 2023] Asynchrony-Robust Collaborative Perception via Bird’s Eye View Flow

DeepPhysicVision/DQ-DETR

DQ-DETR: DETR with Dynamic Query for Tiny Object Detection

DeepPhysicVision/DUSA

[ACM MM 2023] Official implementation of DUSA: Decoupled Unsupervised Sim2Real Adaptation for Vehicle-to-Everything Collaborative Perception

DeepPhysicVision/EMIFF

EMIFF: Enhanced Multi-scale Image Feature Fusion for Vehicle-Infrastructure Cooperative 3D Object Detection

DeepPhysicVision/Far3D

[AAAI2024] Far3D: Expanding the Horizon for Surround-view 3D Object Detection

DeepPhysicVision/gaussian-splatting

Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"

DeepPhysicVision/Hydra-MDP

DeepPhysicVision/LFM

An open source implementation of LFMs from Liquid AI: Liquid Foundation Models

DeepPhysicVision/mamba-minimal

Simple, minimal implementation of the Mamba SSM in one file of PyTorch.

DeepPhysicVision/mamba2-minimal

Minimal Mamba-2 implementation in PyTorch

DeepPhysicVision/MoA

The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>

DeepPhysicVision/nd-Mamba2-torch

Only implemented through torch: "bi - mamba2" , "vision- mamba2 -torch". support 1d/2d/3d/nd and support export by jit.script/onnx;

DeepPhysicVision/OpenSTL

OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning

DeepPhysicVision/Response_Letter_Template

DeepPhysicVision/RWKV-LM

RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.

DeepPhysicVision/simba

Simba

DeepPhysicVision/SUSTechPOINTS

3D Point Cloud Annotation Platform for Autonomous Driving

DeepPhysicVision/TokenMixers

DeepPhysicVision/ttt-lm-pytorch

Official PyTorch implementation of Learning to (Learn at Test Time): RNNs with Expressive Hidden States

DeepPhysicVision/UAV3D

DeepPhysicVision/UniTR

[ICCV2023] Official Implementation of "UniTR: A Unified and Efficient Multi-Modal Transformer for Bird’s-Eye-View Representation"

DeepPhysicVision/VSSD

Introduce Mamba2 to Vision.

DeepPhysicVision/x-transformers

A simple but complete full-attention transformer with a set of promising experimental features from various papers