Skip to content
OpenAgentSkill
Browsing is open · Catalog captured 2026-11-21 · Automatic updates and account services are paused.
DevOps & cloud

3dgs-compression-deploy

3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment, hardware acceleration (Tensor Core/GEMM/FPGA/ASIC), training-free semantic compression. Covers 53+ methods across 6 compression categories. Use when: compressing 3DGS models, deploying 3DGS to web/mobile/edge, selecting quantization bit-width, designing streaming pipelines, 3DGS压缩/量化/剪枝/部署/流式传输/移动端/硬件加速.

jaccen · AI review on file

Installation

Read the source and dependencies before running a command. Copying does not install or execute anything.

npx skills add jaccen/Awesome-Gaussian-Skills --skill 3dgs-compression-deploy

About this skill


name: 3dgs-compression-deploy description: "3DGS compression-to-deployment pipeline: quantization (scalar/VQ/mixed-precision), pruning (coreset/adaptive/variational/merge/Bayesian), progressive streaming & LoD, Web/WebGPU/mobile deployment, hardware acceleration (Tensor Core/GEMM/FPGA/ASIC), training-free semantic compression. Covers 53+ methods across 6 compression categories. Use when: compressing 3DGS models, deploying 3DGS to web/mobile/edge, selecting quantization bit-width, designing streaming pipelines, 3DGS压缩/量化/剪枝/部署/流式传输/移动端/硬件加速." license: Apache-2.0 user-invocable: true metadata: version: "1.1.1" author: jaccen tags: ["3dgs", "gaussian-splatting", "compression", "quantization", "pruning", "vector-quantization", "streaming", "deployment", "mobile", "webgpu", "tensor-core", "hardware-acceleration", "bayesian", "semantic-compression"] when_to_use: - "Compress a 3DGS model for storage or transmission" - "Deploy 3DGS to web browser, mobile device, or edge hardware" - "Select quantization scheme, bit-width, or pruning strategy" - "Design progressive streaming or Level-of-Detail pipeline" - "Evaluate hardware acceleration options (Tensor Core, GEMM, FPGA, ASIC)" - "3DGS压缩 / 量化 / 剪枝 / 部署 / 流式传输 / 移动端 / 硬件加速"

3DGS Compression & Deployment

End-to-end pipeline from raw 3DGS model to deployed application. Covers 6 compression categories + 4 deployment targets + hardware acceleration.

Capabilities

  • Analyze 3DGS model attributes (position, SH, opacity, scale, rotation) and recommend compression strategy
  • Select quantization method and bit-width per attribute (scalar, VQ, mixed-precision)
  • Design pruning pipeline (coreset, adaptive, variational, merge-based)
  • Plan VQ codebook architecture and residual coding
  • Architect progressive streaming and LoD systems (static and 4D dynamic)
  • Guide platform-specific deployment (WebGL, WebGPU, iOS/Android, desktop)
  • Evaluate hardware acceleration paths (Tensor Core, GEMM, FPGA, ASIC)
  • Estimate compression ratio, quality loss, and rendering speed for each method combination

Compression Pipeline

Raw 3DGS Model
    │
    ▼
[Step 1] Analysis ── attribute profiling, bottleneck identification
    │
    ▼
[Step 2] Strategy Selection ── target platform → compression recipe
    │
    ▼
[Step 3] Pruning ── reduce Gaussian count (coreset / adaptive / variational / merge)
    │
    ▼
[Step 4] Quantization ── reduce per-attribute bit-width (scalar / VQ / mixed-precision)
    │
    ▼
[Step 5] Vector Quantization ── codebook-based attribute compression (optional, replaces/augments Step 4)
    │
    ▼
[Step 6] Streaming & LoD ── progressive loading structure for network delivery
    │
    ▼
[Step 7] Deployment ── platform-specific renderer and runtime
    │
    ▼
Deployed Application (Web / Mobile / Desktop / Edge)

Step 1: Analysis

Profile the 3DGS model before selecting compression methods:

AttributeFP32 SizeTypical RangeSensitivity to Quantization
Position (μ)12B/GaussianScene boundsHigh — direct geometry impact
SH (degree 0–3)48B/Gaussian[-1, 1] per coeffMedium-High — visual quality driver
Opacity (α)4B/Gaussian[0, 1]Medium — pruning signal
Scale (s)12B/Gaussian[1e-5, 1e2]Medium — anisotropy sensitive
Rotation (q)16B/GaussianUnit quaternionLow-Medium — can tolerate 8-bit

Profiling checklist:

  1. Total Gaussian count N and file size S
  2. Target platform constraints (memory budget, bandwidth, GPU capability)
  3. Quality floor (minimum acceptable PSNR/SSIM)
  4. Required FPS threshold
  5. Whether dynamic (4DGS) or static scene

Step 2: Compression Strategy Selection

Decision tree by target platform:

Target Platform?
├── Web (WebGL/WebGPU)
│   ├── Bandwidth-limited → Pruning + VQ + Streaming (CAGS/HGS pipeline)
│   └── Compute-limited → Aggressive pruning + low SH degree + Flux-GS
├── Mobile (iOS/Android)
│   ├── Real-time required → Mobile-GS pipeline (depth-aware OIT + distillation + pruning)
│   └── Quality priority → MesonGS++ (mixed-precision, budget-controlled) + NanoGS merge
├── Desktop (GPU ≥ RTX 3060)
│   ├── Max quality → Light quantization only (8-10 bit, ContextGS entropy coding)
│   └── Large scene → Pruning + Streaming + HiGS hierarchical tiles
└── Edge / Embedded
    ├── FPGA targeted → SpqGS (hardware-friendly quantization) + Axis-Shared Accelerator
    └── Low-power GPU → VEDAL pruning + 4-6 bit quantization + PocketGS on-device

Combined target table:

TargetTypical Gaussian BudgetBit-width RangeStreamingKey Methods
Web100K–500K4–8 bitRequiredCAGS, StreamLoD-GS, Spark 2.0
Mobile50K–200K4–8 bitOptionalMobile-GS, Flux-GS, PocketGS
Desktop500K–5M8–16 bitFor large scenesMesonGS++, HiGS, gsplat
Edge/FPGA10K–100K2–6 bitRequiredSpqGS, VEDAL, GEMM-GS

Step 3: Quantization

Method Selection

MethodTypeVenueBit-widthKey Feature
MesonGS++Mixed-precision (post-training)arXiv 20264–16 bit per attribute0-1 ILP hyperparameter search, 34x compression
GETA-3DGSJoint pruning + quantizationarXiv 20264–8 bit heterogeneousRender-aware saliency, QADG dependency graph
GSQLearned step sizeCVPR 20254–8 bitGroup-wise quantization with learnable step
ContextGSContext-model entropy codingNeurIPS 20248–16 bitAnchor-level context replaces uniform quant
SpqGSScalable parallelCVPR 2025Hardware-friendlyParallel bit allocation for FPGA/ASIC
SOG-GSChannel-groupedCVPR 2025Per-channelPreserves inter-Gaussian correlations
ZipGSPruning + quant + entropyCVPR 2025VariableVolumetric entropy coding
GaussianCodec
Read the complete source ↗