印刻万物 TOP3DGS印刻万物TOP3DGS
Back to Learn

Learning Path

Capture & Training Workflow

From lighting and lenses to SfM and training params: an end-to-end pipeline from reality to Gaussians

Level

Intermediate

Duration

约 4 小时

Audience

Creators, photographers and developers who want to capture and train splats themselves

Prerequisites

  • Completed Path 01 or already grasp the basics of 3DGS
  • Have a phone, camera or action cam available
  • Willing to follow capture protocols and tolerate training waits

After this path you can

  • Build a pre-shoot checklist for 3DGS-ready captures
  • Master capture routes for small rooms, objects and large spaces
  • Choose between cloud and local training with cost awareness
  • Use SuperSplat and splat-transform for QC, cleanup and export
  • Establish a reusable capture-preprocess-train-export workflow template

Modules

8 modules, layered understanding

  1. Module 01Article
    25 分钟

    Pre-shoot Engineering: Light, Sharpness & Overlap

    Treat capture as engineering rather than improvisation. This module consolidates the three foundational variables — lighting, focus sharpness and frame overlap — and offers a pre-shoot self-check list to keep training runs from paying interest on lazy capture.

    What's inside

    1. 01Why 3DGS cares more about light consistency than color temperature
    2. 02Judging sharpness: from focal points to motion blur
    3. 03Overlap rule of thumb: 70% horizontal, 60% vertical
    4. 04The eight-item pre-shoot checklist
  2. Module 02Tutorial
    30 分钟

    The Three-Layer Capture Method

    Picture the space as an onion: shoot in three concentric layers. This module walks through the回字-shaped path design, lens-height hierarchy, and how to keep cameras from photographing each other inside cramped venues.

    What's inside

    1. 01Geometric meaning of three rings: high, mid and low viewpoints
    2. 02回-shaped paths and loop closure: making SfM converge
    3. 03Small-space tactics: avoiding lens-in-frame and occlusion
    4. 04Hands-on: a full route with Scaniverse / Luma
  3. Module 03Tutorial
    30 分钟

    Object Video Capture: Phone Hands-on

    Recording an object on your phone is the lowest-barrier entry into 3DGS. This module shares reusable grip, pacing and shot lists so a single object becomes training-ready footage within ninety seconds.

    What's inside

    1. 01Grip and stabilization: killing high-frequency jitter
    2. 02Pacing: a 15-degree-per-second orbit
    3. 03Three-shot script: top-down, eye-level, low-angle
    4. 04Luma vs Scaniverse: experience-level differences
  4. Module 04Tutorial
    30 分钟

    Object Photo Capture: Studio Setup

    Stepping into a studio means controlling every photon. This module covers the turntable-plus-black-cloth minimal rig, ideal angular spacing between shots, and how KIRI's Remy workflow turns photo pipelines into a near push-button experience.

    What's inside

    1. 01Turntable plus dual softbox: a minimal studio
    2. 02Angle spacing: every 5 degrees or every 10
    3. 03Polycam vs KIRI Engine in the photo pipeline
    4. 04Where Remy's automation breaks and what it costs
  5. Module 05Tutorial
    35 分钟

    Action Cams & 360 Cams: Large-space Capture

    When the venue grows from a single room to an entire courtyard, phones run out of breath. This module benchmarks Insta360 panoramic rigs, DJI Terra aerial routes, and Monogram's Japan field practice so you can pick a kit matching your terrain.

    What's inside

    1. 01360 cam advantages of FOV redundancy and dewarping pitfalls
    2. 02Drone surveying: DJI Terra waypoint planning
    3. 03Action cam choreography: handheld stability and trajectory
    4. 04After the shoot: frame extraction and redundancy trimming
  6. Module 06Video
    35 分钟

    Local Training 101: Postshot / Brush / Lichtfeld Studio

    Local training marks the crossover from hobbyist to practitioner. Anchored on three desktop tools that are free or low-cost, this module spells out VRAM budgets, step counts and convergence heuristics — including a what-to-do-when-it-crashes routine.

    What's inside

    1. 01Postshot: drag-and-train desktop experience
    2. 02Brush: customizable open-source trainer
    3. 03Lichtfeld Studio: a research-leaning engineered trainer
    4. 04Reading training logs: loss curves and splat-count evolution
  7. Module 07Article
    25 分钟

    Cloud Training: Luma / Zhitianxia / Pointcosm

    When local hardware buckles, the cloud is the other leg. This module benchmarks Luma's minimalist uploads, Zhitianxia's enterprise-leaning platform, and Pointcosm's package-based pricing, with a selection matrix indexed by scene scale.

    What's inside

    1. 01Upload UX: from front-end UI to failure retries
    2. 02Benchmarking training time against price
    3. 03Export formats: ply vs splat vs spz trade-offs
    4. 04Enterprise platforms vs packaged plans
  8. Module 08Tutorial
    30 分钟

    Validation & Export: QC + Format Choice

    Training done is just round one of quality control. This module shows how to delete floaters in SuperSplat, convert formats with splat-transform, and grade outputs against a simple PSNR/SSIM/LPIPS rubric.

    What's inside

    1. 01Lasso and delete floaters in SuperSplat
    2. 02Convert ply / splat / spz with splat-transform
    3. 03Self-evaluation with PSNR / SSIM / LPIPS
    4. 04Final delivery checklist before handing off

Put it to work

After this path, head to the tool index, assemble a capture-plus-trainer kit, and scan the room you know best as your first homework.

Browse Tools Index