yxchng

superpoint_transformer

Official PyTorch implementation of Superpoint Transformer introduced in [ICCV'23] "Efficient 3D Semantic Segmentation with Superpoint Transformer" and SuperCluster introduced in [3DV'24 Oral] "Scalable 3D Panoptic Segmentation As Superpoint Graph Clustering"

EMO

[ICCV 2023] Official PyTorch implementation of "Rethinking Mobile Block for Efficient Attention-based Models"

FeatUp

Official code for "FeatUp: A Model-Agnostic Frameworkfor Features at Any Resolution" ICLR 2024

DiT-3D

🔥🔥🔥Official Codebase of "DiT-3D: Exploring Plain Diffusion Transformers for 3D Shape Generation"

rnn-icrag

Official repository of paper "RNNs Are Not Transformers (Yet): The Key Bottleneck on In-context Retrieval"

SgMg

[ICCV 2023] Spectrum-guided Multi-granularity Referring Video Object Segmentation.

VD-IT

CAGroup3D

[NeurIPS2022] This is the official code of "CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Clouds".

Swin3D

A shift-window based transformer for 3D sparse tasks

LocalMamba

Code for paper LocalMamba: Visual State Space Model with Windowed Selective Scan

3detr

Code & Models for 3DETR - an End-to-end transformer model for 3D object detection

V-DETR

[ICLR 2024] This is the official code of the paper "V-DETR: DETR with Vertex Relative Position Encoding for 3D Object Detection"

PCM

Point Could Mamba: Point Cloud Learning via State Space Model

PointMamba

PointMamba: A Simple State Space Model for Point Cloud Analysis

Awesome-state-space-models

Collection of papers on state-space models

IMProv

IMProv: Inpainting-based Multimodal Prompting for Computer Vision Tasks

Patch-Aligned-Contrastive-Learning

YOLO-World

[CVPR 2024] Real-Time Open-Vocabulary Object Detection

GaLore

GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection

SLD

🔥 [CVPR2024] Official implementation of "Self-correcting LLM-controlled Diffusion Models (SLD)

VMamba

VMamba: Visual State Space Models，code is based on mamba

Vision-RWKV

Vision-RWKV: Efficient and Scalable Visual Perception with RWKV-Like Architectures

LLaVA-HR

LLaVA-HR: High-Resolution Large Language-Vision Assistant

DCNv4

[CVPR 2024] Deformable Convolution v4

devit

VisionLLaMA

VisionLLaMA: A Unified LLaMA Backbone for Vision Tasks

MobileVLM

Strong and Open Vision Language Assistant for Mobile Devices

DVIS

DVIS: Decoupled Video Instance Segmentation Framework

TOAST

Official code for "TOAST: Transfer Learning via Attention Steering"

ovsam

[arXiv preprint] The official code of paper "Open-Vocabulary SAM".