⚡ Conquer3D

High-Performance GPU-Accelerated Differentiable Geometry, Spatial Computing & Neural Rendering Toolbox

🌐 Website • Guide • API Reference • Benchmarks • Results • Installation

---

Note

The API documentation, the documentation website, and version control tasks were written and automated with Claude. The library itself — every CUDA kernel, data structure and operator — is the author's own work.

---

🌟 Overview

Conquer3D is an ultra-fast, GPU-native computational geometry and differentiable spatial computing library engineered in PyTorch and CUDA. Designed from the ground up for 3D computer vision, generative AI, neural surface reconstruction, and differentiable rendering, Conquer3D delivers up to ~1.3 Billion faces/second isosurface extraction, exact CAD sharp crease preservation, and memory-efficient spatial acceleration structures.

Every operator consumes and produces PyTorch tensors in place — no host round-trip, no format conversion — so meshing a field is an operation inside a training step rather than a preprocessing stage around it.

pip install -U conquer3d

import torch
from conquer3d.data_structure import create_voxel_grid
from conquer3d.ops import dmc

grid_vertices, voxels, _ = create_voxel_grid(
    grid_min=[-1.0] * 3, grid_max=[1.0] * 3, res=[64, 64, 64], device="cuda"
)

sdf = (torch.norm(grid_vertices, dim=-1) - 0.6).requires_grad_(True)
verts, faces = dmc(grid_vertices, voxels, sdf, iso=0.0)

verts.sum().backward()          # gradients flow back into the field

---

🔬 Qualitative Results

Isosurface extraction

One signed distance field meshed by four different extractors.

Sharp features

Exact Hermite data lets the dual methods reconstruct a crease instead of rounding it.

Grid resolution

The same model extracted from 64³ up to 2048³, with the error measured at each step.

Extraction pipeline

Every stage of one extraction, from input mesh to extracted surface.

Sign modes

One slice through each of two meshes, signed by all seven ways of deciding inside.

Ray queries

Which triangles and which voxels a ray hits, found through the BVH.

---

⚡ Benchmarks

RTX 4090, torch 2.8.0+cu128, CUDA 12.8. Fandisk at $1024^3$ (5.15M active cells). CUDA events around the operator alone, median of 7 runs after 2 warm-ups.

Algorithm	Output	Vertices	Faces	Latency	Throughput
Dual Marching Cubes	Triangles	1,716,384	3,432,764	2.62 ms	1,311M faces/s
DMC (pure quads)	Quads	1,716,384	1,716,382	2.51 ms	684M quads/s
MC Asymptotic	Triangles	1,716,382	3,432,760	2.71 ms	1,267M faces/s
Dual Contouring	Triangles	1,716,384	3,432,764	3.88 ms	884M faces/s
Marching Cubes	Triangles	1,716,382	3,432,760	7.90 ms	434M faces/s
Marching Tetrahedra	Triangles	6,113,918	12,227,832	44.90 ms	272M faces/s

Sign-mode costs, distance-operator throughput, pipeline breakdown and memory scaling are on the benchmarks page.

---

📦 Installation

pip install -U conquer3d

Building from source, the full feature list, worked pipelines and the complete API reference are on the documentation site.

---

📄 License

Conquer3D is licensed under the MIT License.

_{Built with CUDA and PyTorch · khoidoo.github.io/conquer3d}