siyandong

ShiArthur03

PyTorch-VAE

A Collection of Variational Autoencoders (VAE) in PyTorch.

Mono3D

Source code for "Mononizing Binocular Videos" (SIGGRAPH Asia 2020)

multi-scene-pose-transformer

Multi-Scene Camera Pose Regression with Transformers

Wonder3D

Single Image to 3D using Cross-Domain Diffusion for 3D Generation

CLIP

CLIP (Contrastive Language-Image Pretraining), Predict the most relevant text snippet given an image

llama

Inference code for Llama models

LightGlue

LightGlue: Local Feature Matching at Light Speed (ICCV 2023)

FoundationPose

[CVPR 2024 Highlight] FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects

MonoGS

[CVPR'24 Highlight & Best Demo Award] Gaussian Splatting SLAM

dust3r

DUSt3R: Geometric 3D Vision Made Easy

3D-LLM

Code for 3D-LLM: Injecting the 3D World into Large Language Models

NeuS

Code release for NeuS

nerf-pytorch

A PyTorch implementation of NeRF (Neural Radiance Fields) that reproduces the results.

grok

objaverse-xl

🪐 Objaverse-XL is a Universe of 10M+ 3D Objects. Contains API Scripts for Downloading and Processing!

Depth-Anything

[CVPR 2024] Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data. Foundation Model for Monocular Depth Estimation

generative-models

Generative Models by Stability AI

gim

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

DiT

Official PyTorch Implementation of "Scalable Diffusion Models with Transformers"

SyncDreamer

[ICLR 2024 Spotlight] SyncDreamer: Generating Multiview-consistent Images from a Single-view Image

Amodal-Completion-in-the-Wild

BlendedMVS

BlendedMVS: A Large-scale Dataset for Generalized Multi-view Stereo Networks

PoseLib

Minimal solvers for calibrated camera pose estimation

Uni3D

[ICLR'24 Spotlight] Uni3D: 3D Visual Representation from BAAI

dot

Dense Optical Tracking: Connecting the Dots

ace

[CVPR 2023 - Highlight] Accelerated Coordinate Encoding (ACE): Learning to Relocalize in Minutes using RGB and Poses

LVM

instant-nsr-pl

Neural Surface reconstruction based on Instant-NGP. Efficient and customizable boilerplate for your research projects. Train NeuS in 10min!

LLaVA

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.