Puhua Jiang (puhuajiang)

puhuajiang

Geek Repo

Company:Tsinghua University

Location:Shen Zheng

Home Page:puhuajiang.github.io

Github PK Tool:Github PK Tool

Puhua Jiang's starred repositories

google-research

Google Research

Language:Jupyter NotebookLicense:Apache-2.0Stargazers:34014Issues:751Issues:1250

generative-models

Generative Models by Stability AI

Language:PythonLicense:MITStargazers:24297Issues:257Issues:304

Hierarchical-Localization

Visual localization made easy with hloc

Language:PythonLicense:Apache-2.0Stargazers:3137Issues:88Issues:304

LayerDiffuse

Transparent Image Layer Diffusion using Latent Transparency

LGM

[ECCV 2024 Oral] LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content Creation.

Language:PythonLicense:MITStargazers:1599Issues:33Issues:70

FeatUp

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

Language:Jupyter NotebookLicense:MITStargazers:1346Issues:18Issues:63

pycolmap

Python bindings for COLMAP

Language:C++License:BSD-3-ClauseStargazers:901Issues:18Issues:154

pixelsplat

[CVPR 2024 Oral, Best Paper Runner-Up] Code for "pixelSplat: 3D Gaussian Splats from Image Pairs for Scalable Generalizable 3D Reconstruction" by David Charatan, Sizhe Lester Li, Andrea Tagliasacchi, and Vincent Sitzmann

Language:PythonLicense:MITStargazers:849Issues:20Issues:97

splatter-image

Official implementation of `Splatter Image: Ultra-Fast Single-View 3D Reconstruction' CVPR 2024

Language:PythonLicense:BSD-3-ClauseStargazers:831Issues:26Issues:54

webvid

Large-scale text-video dataset. 10 million captioned short videos.

CRM

[ECCV 2024] Single Image to 3D Textured Mesh in 10 seconds with Convolutional Reconstruction Model.

Language:PythonLicense:MITStargazers:549Issues:19Issues:25

Text2Tex

[ICCV 2023] Text2Tex: Text-driven Texture Synthesis via Diffusion Models

Language:PythonLicense:NOASSERTIONStargazers:547Issues:39Issues:31

RayDiffusion

Code for "Cameras as Rays"

Language:PythonLicense:MITStargazers:494Issues:12Issues:28

gim

GIM: Learning Generalizable Image Matcher From Internet Videos (ICLR 2024 Spotlight)

Language:PythonLicense:MITStargazers:472Issues:21Issues:27

COTR

Code release for "COTR: Correspondence Transformer for Matching Across Images"(ICCV 2021)

Language:PythonLicense:Apache-2.0Stargazers:457Issues:12Issues:47

V3D

V3D: Video Diffusion Models are Effective 3D Generators

epipolar-transformers

Epipolar Transformers (best paper award, CVPR 2020 workshop)

Language:Jupyter NotebookLicense:MITStargazers:413Issues:21Issues:33

differentiable-blocksworld

[NeurIPS 2023] Code for "Differentiable Blocks World: Qualitative 3D Decomposition by Rendering Primitives"

Language:PythonLicense:MITStargazers:197Issues:8Issues:11

bidiff

[CVPR'24] Text-to-3D Generation with Bidirectional Diffusion using both 2D and 3D priors

Language:PythonLicense:Apache-2.0Stargazers:160Issues:16Issues:7

RIVAL

[NeurIPS 2023 Spotlight] Real-World Image Variation by Aligning Diffusion Inversion Chain

Language:PythonLicense:Apache-2.0Stargazers:142Issues:17Issues:8
Language:Jupyter NotebookLicense:Apache-2.0Stargazers:78Issues:2Issues:13

NEF_code

Code for the CVPR 2023 paper "NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-view Images".

DiffusionReg

SE(3) Diffusion Model-based Point Cloud Registration for Robust 6D Object Pose Estimation (Accepted by NeurIPS-2023)

Language:PythonLicense:MITStargazers:73Issues:7Issues:11

MicroDiffusion

[CVPR 2024] This repository includes the official implementation our paper "MicroDiffusion: Implicit Representation-Guided Diffusion for 3D Reconstruction from Limited 2D Microscopy Projections"

DiffSF

Official repository for paper: DiffSF: Diffusion Models for Scene Flow Estimation

Language:PythonStargazers:18Issues:2Issues:0

Point2SSM

Point2SSM: Learning Morphological Variations of Anatomies from Point Cloud

ReebGraph

Implementation of the Reeb Graph model for neuronal fibers

Language:PythonStargazers:2Issues:2Issues:0
Language:PythonStargazers:1Issues:1Issues:0