nerfstudio-project/nerfstudio

Allow gaussian splatting to initialize start points from other data pipelines than COLMAP

Open

#2,681 opened on Dec 15, 2023

View on GitHub
 (14 comments) (15 reactions) (0 assignees)Python (819 forks)batch import
custom datasetgood first issue

Repository metrics

Stars
 (6,659 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

Currently, gaussian splatting intakes a pointcloud for initialization either through: 1) using a COLMAP dataset, or 2) adding a pointcloud to transforms.json and using the nerfstudio dataparser to read it. Currently, data intake pipelines like polycam, metashape, etc do not output a pointcloud and thus gaussian splatting will use a random initialization of points, which produces much worse results.

To fix this, we should edit the data intake scripts to add point clouds to the output transforms.json files and use the nerfstudio dataparser to read them. #2557 added the capability to load .ply files in the nerfstudio dataparser

  • Add to the COLMAP data processing pipeline to save pointclouds of the SFM points as output, and add it to the transforms.json
  • Switch to nerfstudio dataparser as the default for splatting
  • implement pointcloud saving in other data processing pipelines

Contributor guide

Research direction
Study the existing COLMAP data processing pipeline (e.g., colmap data.py) to understand how point clouds are saved and added to transforms.json. Then implement similar functionality for other pipelines such as polycam and metashape by editing their respective data processing scripts.
Tech stack
None
Domain
computer graphics
Issue type
Feature
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Clear
Prerequisites
PythonGaussian SplattingCOLMAP
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
60