• Stars
    star
    287
  • Rank 144,232 (Top 3 %)
  • Language
    Python
  • License
    MIT License
  • Created 8 months ago
  • Updated 4 months ago

Reviews

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Repository Details

Code for "Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting" by Jaewoo Jung, Jisang Han, Honggyu An, Jiwon Kang, Seonghoon Park, and Seungryong Kim

RAIN-GS: Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting


This is our official implementation of the paper "Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting"!

by Jaewoo Jung, Jisang Han, Honggyu An, Jiwon Kang, Seonghoon Park, Seungryong Kim

☔: Equal Contribution
†: Corresponding Author

Introduction


We introduce a novel optimization strategy (RAIN-GS) for 3D Gaussian Splatting!

We show that our simple yet effective strategy consisted of sparse-large-variance (SLV) random initialization and progressive Gaussian low-pass filter control robustly guides 3D Gaussians to model the scene even when starting from random point clouds.

For further details and visualization results, please check out our paper and our project page.

Installation

We implement RAIN-GS above the official implementation of 3D Gaussian Splatting.
For environmental setup, we kindly guide you to follow the original requirements of 3DGS.

Training

To train 3D Gaussian Splatting with our novel strategy (RAIN-GS), all you need to do is:

python train.py -s {dataset_path} --exp_name {exp_name} --eval --ours

For dense-small-variance (DSV) random initialization (used in the original 3D Gaussian Splatting), you can simply run with the following command:

python train.py -s {dataset_path} --exp_name {exp_name} --eval --DSV

To train with Mip-NeRF360 dataset, you can add argument --images images_4 for outdoor scenes and --images images_2 for indoor scenes to modify the resolution of the input images.

Acknowledgement

We would like to acknowledge the contributions of 3D Gaussian Splatting for open-sourcing the official codes for 3DGS!

Citation

If you find our work helpful, please cite our work as:

@article{jung2024relaxing,
  title={Relaxing Accurate Initialization Constraint for 3D Gaussian Splatting},
  author={Jung, Jaewoo and Han, Jisang and An, Honggyu and Kang, Jiwon and Park, Seonghoon and Kim, Seungryong},
  journal={arXiv preprint arXiv:2403.09413},
  year={2024}
}

More Repositories

1

3DFuse

Official implementation of "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation"
Python
561
star
2

CAT-Seg

Official Implementation of "CAT-Seg🐱: Cost Aggregation for Open-Vocabulary Semantic Segmentation"
Python
244
star
3

GaussianTalker

Official implementation of “GaussianTalker: Real-Time High-Fidelity Talking Head Synthesis with Audio-Driven 3D Gaussian Splatting” by Kyusun Cho, Joungbin Lee, Heeji Yoon, Yeobin Hong, Jaehoon Ko, Sangjun Ahn and Seungryong Kim
Python
209
star
4

LANIT

Official repository for LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data (CVPR 2023)
Python
137
star
5

DiffMatch

Official implementation of "Diffusion Model for Dense Matching" (ICLR'24 Oral)
Python
135
star
6

MoDiTalker

Python
133
star
7

Talk3D

Python
127
star
8

3DGAN-Inversion

Official Implementation of WACV 2023 paper "3D GAN Inversion with Pose Optimization".
Python
107
star
9

locotrack

Official implementation of "Local All-Pair Correspondence for Point Tracking" (ECCV 2024)
Python
106
star
10

NeMF

Official code implementation of NeMF (NeurIPS'22)
Python
83
star
11

DirecT2V

Python
75
star
12

MIDMs

Official code implementation of MIDMs: Matching Interleaved Diffusion Models for Exemplar-based Image Translation (AAAI'23)
Python
65
star
13

DaRF

Official code implementation of "DäRF: Boosting Radiance Fields from Sparse Inputs with Monocular Depth Adaptation"(NeurIPS 2023)
Python
64
star
14

InstaFormer

Official repository for InstaFormer: Instance-aware Image-to-Image Translation with Transformer (CVPR 2022)
Python
51
star
15

CATs-PlusPlus

Official repository for CATs++: Boosting Cost Aggregation with Convolutions and Transformers (TPAMI'22)
Python
42
star
16

MaskingDepth

Python
39
star
17

DAG

33
star
18

INR-st

Official repository for Controllable Style Transfer via Test-time Training of Implicit Neural Representation
Python
28
star
19

GeCoNeRF

HTML
28
star
20

SE-NeRF

16
star
21

MoA

Mixture-of-Adapters
Python
15
star
22

SplitNet

11
star
23

RetDream

Official implementation of "Retrieval-Augmented Score Distillation for Text-to-3D Generation"
5
star
24

CATs-PlusPlus-Project-Page

HTML
5
star
25

3DFuse-threestudio

Threestudio extension of the paper "Let 2D Diffusion Model Know 3D-Consistency for Robust Text-to-3D Generation".
Python
2
star
26

GSD

Geometry-Aware Score Distillation via 3D Consistent Noising and Gradient Consistency Modeling
1
star