lorenmt

Shikun Liu's starred repositories

StableCascade

Official Code for Stable Cascade

Language:Jupyter NotebookMIT6448 61 121

dust3r

DUSt3R: Geometric 3D Vision Made Easy

Language:PythonNOASSERTION4739 54 115

ml-mgie

Language:PythonNOASSERTION3807 630

kubric

A data generation pipeline for creating semi-realistic synthetic multi-object videos with rich annotations such as instance segmentation masks, depth maps, and optical flow.

Language:Jupyter NotebookApache-2.02235 42 184

Marigold

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

Language:PythonApache-2.02056 43 67

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

Language:Jupyter NotebookApache-2.02036 34 79

ml-hypersim

Hypersim: A Photorealistic Synthetic Dataset for Holistic Indoor Scene Understanding

Language:PythonNOASSERTION1626 42 68

multimodal

TorchMultimodal is a PyTorch library for training state-of-the-art multimodal multi-task models at scale.

Language:PythonBSD-3-Clause1376 22 38

GaLore

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

Language:PythonApache-2.01275 17 46

MonoGS

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

Language:PythonNOASSERTION1129 14 106

DSINE

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Language:Jupyter NotebookNOASSERTION632 9 7

GeoWizard

[ECCV'24] GeoWizard: Unleashing the Diffusion Priors for 3D Geometry Estimation from a Single Image

Language:Python625 22 24

SiT

Official PyTorch Implementation of "SiT: Exploring Flow and Diffusion-based Generative Models with Scalable Interpolant Transformers"

Language:PythonMIT557 10 18

magvit2-pytorch

Implementation of MagViT2 Tokenizer in Pytorch

Language:PythonMIT495 30 33

MDT

Masked Diffusion Transformer is the SOTA for image synthesis. (ICCV 2023)

Language:PythonApache-2.0488 18 45

V3D

V3D: Video Diffusion Models are Effective 3D Generators

Language:Python431 15 26

VBench

[CVPR2024 Highlight] VBench - We Evaluate Video Generation

Language:PythonApache-2.0403 11 44

TCD

Official Repository of the paper "Trajectory Consistency Distillation"

Language:Python290 10 18

Dataset

News: the 7k dataset is ready for download.

Language:HTMLNOASSERTION260 13 22

laion-3d

Collect large 3d dataset and build models

248 19 4

PUG

This is the repository for the Photorealistic Unreal Graphics (PUG) datasets for representation learning.

Language:Jupyter NotebookNOASSERTION224 8 2

EscherNet

[CVPR2024 Oral] EscherNet: A Generative Model for Scalable View Synthesis

Language:PythonNOASSERTION219 9 8

flatten

Pytorch Implementation of FLATTEN: optical FLow-guided ATTENtion for consistent text-to-video editing (ICLR 2024)

Language:PythonApache-2.0172 8 3

super_primitive

[CVPR'24, Demo Track Honourable Mention] SuperPrimitive: Scene Reconstruction at a Primitive Level

Language:PythonNOASSERTION152 7 1

MVDiffusion_plusplus

MVDiffusion++: A Dense High-resolution Multi-view Diffusion Model for Single or Sparse-view 3D Object Reconstruction

122 22 2

gta

[ICLR'24] GTA: A Geometry-Aware Attention Mechanism for Multi-view Transformers

Language:PythonMIT116 13 1

MorpheuS

[CVPR'24] MorpheuS: Neural Dynamic 360° Surface Reconstruction from Monocular RGB-D Video

Language:PythonApache-2.0115 100

Dream2Real

[ICRA 2024] Dream2Real: Zero-Shot 3D Object Rearrangement with Vision-Language Models

Language:Python45 50

T5-Textual-Inversion

Textual Inversion for DeepFloyd IF

Language:Jupyter NotebookAGPL-3.043 3 1

Den-SOFT

Language:JavaScript500