doubledaibo

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

segment-anything-2

The repository provides code for running inference with the Meta Segment Anything Model 2 (SAM 2), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.

MotionLCM

[ ECCV 2024 ] MotionLCM: This repo is the official implementation of "MotionLCM: Real-time Controllable Motion Generation via Latent Consistency Model"

Director3D

Code for "Director3D: Real-world Camera Trajectory and 3D Scene Generation from Text".

InterScene

[3DV 2024] Official repo of "Synthesizing Physically Plausible Human Motions in 3D Scenes"

PacerPlus

Official implementation of the paper "PACER+: On-Demand Pedestrian Animation Controller in Driving Scenarios" (CVPR 2024).

CRATE

Code for CRATE (Coding RAte reduction TransformEr).

EpiDiff

[CVPR 2024] EpiDiff: Enhancing Multi-View Synthesis via Localized Epipolar-Constrained Diffusion

sd-forge-layerdiffuse

[WIP] Layer Diffusion for WebUI (via Forge)

CameraCtrl

Make-It-Vivid

[CVPR 2024] Make-It-Vivid: Dressing Your Animatable Biped Cartoon Characters from Text

GSDF

GSDF: 3DGS Meets SDF for Improved Rendering and Reconstruction

Octree-GS

Octree-GS: Towards Consistent Real-time Rendering with LOD-Structured 3D Gaussians

LN3Diff

[ECCV-2024] LN3Diff creates high-quality 3D object mesh from text within 8 V100-SECONDS.

dust3r

DUSt3R: Geometric 3D Vision Made Easy

SC-GS

[CVPR 2024] Code for SC-GS: Sparse-Controlled Gaussian Splatting for Editable Dynamic Scenes

jepa

PyTorch code and models for V-JEPA self-supervised learning from video.

Qwen-VL

The official repo of Qwen-VL (通义千问-VL) chat & pretrained large vision language model proposed by Alibaba Cloud.

InternLM-Math

State-of-the-art bilingual open-sourced Math reasoning LLMs.

UniHSI

[ICLR 2024 Spotlight] Unified Human-Scene Interaction via Prompted Chain-of-Contacts

opencompass

OpenCompass is an LLM evaluation platform, supporting a wide range of models (Llama3, Mistral, InternLM2,GPT-4,LLaMa2, Qwen,GLM, Claude, etc) over 100+ datasets.

Open-AnimateAnyone

Unofficial Implementation of Animate Anyone

CoSeR

[CVPR 2024] CoSeR: Bridging Image and Language for Cognitive Super-Resolution

Marigold

[CVPR 2024 - Oral, Best Paper Award Candidate] Marigold: Repurposing Diffusion-Based Image Generators for Monocular Depth Estimation

HIMLoco

Learning-based locomotion control from OpenRobotLab, including Hybrid Internal Model & H-Infinity Locomotion Control

Dataset

News: the 7k dataset is ready for download.

GaussianSplattingViewer

Tiny Gaussian Splatting Viewer

caption-synthesize

DiffMorpher

Official Code for DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing (CVPR 2024)

BerfScene

[CVPR 2024] BerfScene: Bev-conditioned Equivariant Radiance Fields for Infinite 3D Scene Generation