mirror of
https://github.com/allaunthefox/Research-Stack.git
synced 2026-07-31 03:05:21 +00:00
40d8ed3d54
1. Singer Sidon Sets in Lean 4 (2605.03274) — 7541 lines, zero sorry 2. AutoformBot: 45K Lean declarations from 26 textbooks (2605.29955) 3. Rust-to-Lean verification pipeline (2605.30106) 4. Hexagonal lattice + RG + fractal dimension (2605.09974) 5. Burgers + Hopf-Cole unified transform (2605.11788) 6. Self-orthogonal Reed-Solomon → quantum ECC (2605.23460) 7. Hash-based GPU 3D reconstruction (2511.21459) 8. Conjugacy classes of positive 3-braids (2604.16876) 9. Navier-Stokes non-uniqueness (2605.29934) 10. Continuum limit of causal fermion systems (2605.30199) Most relevant to Research Stack: - #1: Direct Sidon set infrastructure for Lean - #4: RG + fractal dimension exact results - #5: Hopf-Cole Burgers (confirms our approach) - #6: RS codes → quantum ECC (VCN pipeline connection)
13 lines
No EOL
1.6 KiB
JSON
13 lines
No EOL
1.6 KiB
JSON
{
|
|
"arxiv_id": "2511.21459",
|
|
"title": "Hash-based GPU 3D Reconstruction",
|
|
"authors": [
|
|
"Lorenzo De Rebotti",
|
|
"Emanuele Giacomini",
|
|
"Giorgio Grisetti",
|
|
"Luca Di Giammarino"
|
|
],
|
|
"abstract": "Abstract:Efficient and scalable 3D surface reconstruction from range data remains a core challenge in computer graphics and vision, particularly in real-time and resource-constrained scenarios. Traditional volumetric methods based on fixed-resolution voxel grids or hierarchical structures like octrees often suffer from memory inefficiency, computational overhead, and a lack of GPU support. We propose a novel variance-adaptive, multi-resolution voxel grid that dynamically adjusts voxel size based on the local variance of signed distance field (SDF) observations. Unlike prior multi-resolution approaches that rely on recursive octree structures, our method leverages a flat spatial hash table to store all voxel blocks, supporting constant-time access and full GPU parallelism. This design enables high memory efficiency and real-time scalability. We further demonstrate how our representation supports GPU-accelerated rendering through a parallel quad-tree structure for Gaussian Splatting, enabling effective control over splat density. Our open-source CUDA/C++ implementation achieves up to 13x speedup and 4x lower memory usage compared to fixed-resolution baselines, while maintaining on par results in terms of reconstruction accuracy, offering a practical and extensible solution for high-performance 3D reconstruction.",
|
|
"url": "https://arxiv.org/abs/2511.21459",
|
|
"pdf_path": "/home/allaun/Research Stack/shared-data/papers/2026-05/2511.21459.pdf"
|
|
} |