Pinned Repositories
shine
[CVPR'24 Highlight] SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection
BirdCheetah-Leg_Design-Modeling-Simulation-DropTest
This repository contains the design of a lightweight robotic leg for research purposes and the Maple modeling and simulation of it. In this repository, you can find the mathematical principle and methods for the modeling and simulation of the kinematics, dynamics and drop test of the designed leg.
class-iNCD
PyTorch implementation for the paper Class-incremental Novel Class Discovery (ECCV 2022)
DGLN-model-for-Person-Re-ID-with-frozen-learning
A parallel CNN architecture - Discriminative-Global- Local Network (DGLN) to exploit both the discriminative structural information at global scope and the discriminative human-introduced local infomration at local level for improvement of re-id task with frozen learning technique.
FineR
[ICLR'24] Democratizing Fine-grained Visual Recognition with Large Language Models
Industrial-Robotics_Modeling-Simulation-Control
This folder focuses on Industrial Robotics study and work
MSc-iNCD
[ICPR'24 Oral] Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
orb_slam3_ros_tube
A ROS wrapper for ORB-SLAM-3 framework. The aim of this wrapper is to subscribe and publish the needed topics in ROS for downstream aglorithms.
Point-cloud-registration_RPA-project
A comparison of using different feature descriptors (SI, SIFT, SHOT, CSHOT, FPFH) and different keypoints detection algorithm (SIFT3D, ISS3D) on point cloud registration (RANSAC + ICP).
Unity_RGB-D_Camera
This is a virtual RGB-D Camera developed in Unity to generate RGB-D point cloud data (.pcd) for experimental purpose. You can import the package (source code included) and use it directly in Unity. Then, you can attach the camera on any Unity Object (a car, a drone or a cat :). Also, you can play with the parameters of the camera, like noises, RGB info or not, FOV, etc. There is a quick start .PDF in the repo. to help you get started. Have fun :)
OatmealLiu's Repositories
OatmealLiu/FineR
[ICLR'24] Democratizing Fine-grained Visual Recognition with Large Language Models
OatmealLiu/class-iNCD
PyTorch implementation for the paper Class-incremental Novel Class Discovery (ECCV 2022)
OatmealLiu/MSc-iNCD
[ICPR'24 Oral] Large-scale Pre-trained Models are Surprisingly Strong in Incremental Novel Class Discovery
OatmealLiu/SMC
OatmealLiu/2d-gaussian-splatting
[SIGGRAPH'24] 2D Gaussian Splatting for Geometrically Accurate Radiance Fields
OatmealLiu/acezero
[ECCV 2024 - Oral] ACE0 is a learning-based structure-from-motion approach that estimates camera parameters of sets of images by learning a multi-view consistent, implicit scene representation.
OatmealLiu/BoxDiff
[ICCV 2023] BoxDiff: Text-to-Image Synthesis with Training-Free Box-Constrained Diffusion
OatmealLiu/CityGaussian
CityGaussian Series for High-quality Large-Scale Scene Reconstruction with Gaussians
OatmealLiu/CLIP
CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image
OatmealLiu/concept-graphs
Official code release for ConceptGraphs
OatmealLiu/Detic
Code release for "Detecting Twenty-thousand Classes using Image-level Supervision".
OatmealLiu/drivestudio
A 3DGS framework for omni urban scene reconstruction and simulation.
OatmealLiu/drkostas.github.io
VScode Portfolio
OatmealLiu/dust3r
DUSt3R: Geometric 3D Vision Made Easy
OatmealLiu/failurecase
OatmealLiu/gaussian-splatting
Original reference implementation of "3D Gaussian Splatting for Real-Time Radiance Field Rendering"
OatmealLiu/Grounded-SAM-2
Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2
OatmealLiu/InstanceDiffusion
[CVPR 2024] Code release for "InstanceDiffusion: Instance-level Control for Image Generation"
OatmealLiu/interactdiffusion
[CVPR 2024] Official repo for "InteractDiffusion: Interaction-Control for Text-to-Image Diffusion Model".
OatmealLiu/LangSplat
Official implementation of the paper "LangSplat: 3D Language Gaussian Splatting" [CVPR2024 Highlight]
OatmealLiu/layout-guidance
[WACV 2024] Training-Free Layout Control with Cross-Attention Guidance
OatmealLiu/llama3
The official Meta Llama 3 GitHub site
OatmealLiu/LLaVA
[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.
OatmealLiu/mast3r
Grounding Image Matching in 3D with MASt3R
OatmealLiu/mvdust3r
Open source impl of **MV-DUSt3R+ Single-Stage Scene Reconstruction from Sparse Views In 2 Seconds** from Meta Reality Labs. Project page https//mv-dust3rp.github.io/
OatmealLiu/nerf
Code release for NeRF (Neural Radiance Fields)
OatmealLiu/nerf_pl
NeRF (Neural Radiance Fields) and NeRF in the Wild using pytorch-lightning
OatmealLiu/ReCo
ReCo: Region-Controlled Text-to-Image Generation, CVPR 2023
OatmealLiu/shine-main
[CVPR'24 Highlight] SHiNe: Semantic Hierarchy Nexus for Open-vocabulary Object Detection
OatmealLiu/VisDiff
Official implementation of "Describing Differences in Image Sets with Natural Language"