LICENSES.md
examples/demo-corpus/LICENSES.md
Demo corpus licenses
Every external source mirrored into examples/demo-corpus/ is listed here with its origin URL, license, and inclusion justification. Sources that aren't on this list aren't in the corpus.
Last updated: 2026-05-15. Compiled by the Phase 1 corpus author.
arXiv paper abstracts (CC0 / public domain)
Per arXiv's policy, abstracts displayed on arXiv abstract pages are not subject to copyright (CC0-equivalent / public domain). The corpus mirrors 50 abstracts verbatim. Each data/research/papers/<slug>/abstract.md carries license: CC0 (arXiv abstract) in its frontmatter and a > Verbatim CC0 abstract mirrored from arXiv quote block.
| # | arXiv id | Title | First author | Year | Sub-topic |
|---|---|---|---|---|---|
| 1 | 2308.04079 | 3D Gaussian Splatting for Real-Time Radiance Field Rendering | Kerbl | 2023 | 3D Gaussian Splatting |
| 2 | 2403.17888 | 2D Gaussian Splatting for Geometrically Accurate Radiance Fields | Huang | 2024 | 3D Gaussian Splatting |
| 3 | 2401.04099 | AGG: Amortized Generative 3D Gaussians for Single Image to 3D | Xu | 2024 | 3D Gaussian Splatting |
| 4 | 2312.02121 | Mathematical Supplement for the $\texttt{gsplat}$ Library | Ye | 2023 | 3D Gaussian Splatting |
| 5 | 2312.00109 | Scaffold-GS: Structured 3D Gaussians for View-Adaptive Rendering | Lu | 2023 | 3D Gaussian Splatting |
| 6 | 2403.14627 | MVSplat: Efficient 3D Gaussian Splatting from Sparse Multi-View Images | Chen | 2024 | 3D Gaussian Splatting |
| 7 | 2402.07207 | GALA3D: Towards Text-to-3D Complex Scene Generation via Layout-guid... | Zhou | 2024 | 3D Gaussian Splatting |
| 8 | 2311.13384 | LucidDreamer: Domain-free Generation of 3D Gaussian Splatting Scenes | Chung | 2023 | 3D Gaussian Splatting |
| 9 | 2312.03203 | Feature 3DGS: Supercharging 3D Gaussian Splatting to Enable Distill... | Zhou | 2023 | 3D Gaussian Splatting |
| 10 | 2403.16292 | latentSplat: Autoencoding Variational Gaussians for Fast Generaliza... | Wewer | 2024 | 3D Gaussian Splatting |
| 11 | 2404.06109 | Revising Densification in Gaussian Splatting | Bulò | 2024 | 3D Gaussian Splatting |
| 12 | 2311.12775 | SuGaR: Surface-Aligned Gaussian Splatting for Efficient 3D Mesh Rec... | Guédon | 2023 | 3D Gaussian Splatting |
| 13 | 2003.08934 | NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis | Mildenhall | 2020 | Neural Radiance Fields |
| 14 | 2103.13415 | Mip-NeRF: A Multiscale Representation for Anti-Aliasing Neural Radi... | Barron | 2021 | Neural Radiance Fields |
| 15 | 2111.12077 | Mip-NeRF 360: Unbounded Anti-Aliased Neural Radiance Fields | Barron | 2021 | Neural Radiance Fields |
| 16 | 2201.05989 | Instant Neural Graphics Primitives with a Multiresolution Hash Enco... | Müller | 2022 | Neural Radiance Fields |
| 17 | 2112.05131 | Plenoxels: Radiance Fields without Neural Networks | Yu | 2021 | Neural Radiance Fields |
| 18 | 2301.10241 | K-Planes: Explicit Radiance Fields in Space, Time, and Appearance | Fridovich-Keil | 2023 | Neural Radiance Fields |
| 19 | 2302.12249 | MERF: Memory-Efficient Radiance Fields for Real-time View Synthesis... | Reiser | 2023 | Neural Radiance Fields |
| 20 | 2008.02268 | NeRF in the Wild: Neural Radiance Fields for Unconstrained Photo Co... | Martin-Brualla | 2020 | Neural Radiance Fields |
| 21 | 2104.06405 | BARF: Bundle-Adjusting Neural Radiance Fields | Lin | 2021 | Neural Radiance Fields |
| 22 | 2103.14024 | PlenOctrees for Real-time Rendering of Neural Radiance Fields | Yu | 2021 | Neural Radiance Fields |
| 23 | 1607.02565 | Direct Sparse Odometry | Engel | 2016 | Visual SLAM and MVS |
| 24 | 2108.10869 | DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Cameras | Teed | 2021 | Visual SLAM and MVS |
| 25 | 2112.12130 | NICE-SLAM: Neural Implicit Scalable Encoding for SLAM | Zhu | 2021 | Visual SLAM and MVS |
| 26 | 2304.14377 | Co-SLAM: Joint Coordinate and Sparse Parametric Encodings for Neura... | Wang | 2023 | Visual SLAM and MVS |
| 27 | 2311.11700 | GS-SLAM: Dense Visual SLAM with 3D Gaussian Splatting | Yan | 2023 | Visual SLAM and MVS |
| 28 | 2312.06741 | Gaussian Splatting SLAM | Matsuki | 2023 | Visual SLAM and MVS |
| 29 | 2304.04278 | Point-SLAM: Dense Neural Point Cloud-based SLAM | Sandström | 2023 | Visual SLAM and MVS |
| 30 | 1812.04605 | DeepV2D: Video to Depth with Differentiable Structure from Motion | Teed | 2018 | Visual SLAM and MVS |
| 31 | 2209.14988 | DreamFusion: Text-to-3D using 2D Diffusion | Poole | 2022 | Diffusion-based 3D Generation |
| 32 | 2211.10440 | Magic3D: High-Resolution Text-to-3D Content Creation | Lin | 2022 | Diffusion-based 3D Generation |
| 33 | 2303.11328 | Zero-1-to-3: Zero-shot One Image to 3D Object | Liu | 2023 | Diffusion-based 3D Generation |
| 34 | 2305.16213 | ProlificDreamer: High-Fidelity and Diverse Text-to-3D Generation wi... | Wang | 2023 | Diffusion-based 3D Generation |
| 35 | 2309.16653 | DreamGaussian: Generative Gaussian Splatting for Efficient 3D Conte... | Tang | 2023 | Diffusion-based 3D Generation |
| 36 | 2306.17843 | Magic123: One Image to High-Quality 3D Object Generation Using Both... | Qian | 2023 | Diffusion-based 3D Generation |
| 37 | 2106.10689 | NeuS: Learning Neural Implicit Surfaces by Volume Rendering for Mul... | Wang | 2021 | Mesh and Surface Reconstruction |
| 38 | 2106.12052 | Volume Rendering of Neural Implicit Surfaces | Yariv | 2021 | Mesh and Surface Reconstruction |
| 39 | 2002.10099 | Implicit Geometric Regularization for Learning Shapes | Gropp | 2020 | Mesh and Surface Reconstruction |
| 40 | 2104.10078 | UNISURF: Unifying Neural Implicit Surfaces and Radiance Fields for ... | Oechsle | 2021 | Mesh and Surface Reconstruction |
| 41 | 2206.00665 | MonoSDF: Exploring Monocular Geometric Cues for Neural Implicit Sur... | Yu | 2022 | Mesh and Surface Reconstruction |
| 42 | 2011.12948 | Nerfies: Deformable Neural Radiance Fields | Park | 2020 | Dynamic and 4D Reconstruction |
| 43 | 2106.13228 | HyperNeRF: A Higher-Dimensional Representation for Topologically Va... | Park | 2021 | Dynamic and 4D Reconstruction |
| 44 | 2105.06468 | Dynamic View Synthesis from Dynamic Monocular Video | Gao | 2021 | Dynamic and 4D Reconstruction |
| 45 | 2310.08528 | 4D Gaussian Splatting for Real-Time Dynamic Scene Rendering | Wu | 2023 | Dynamic and 4D Reconstruction |
| 46 | 2402.03307 | 4D-Rotor Gaussian Splatting: Towards Efficient Novel View Synthesis... | Duan | 2024 | Dynamic and 4D Reconstruction |
| 47 | 2311.04400 | LRM: Large Reconstruction Model for Single Image to 3D | Hong | 2023 | Generative 3D Representations |
| 48 | 2403.02151 | TripoSR: Fast 3D Object Reconstruction from a Single Image | Tochilkin | 2024 | Generative 3D Representations |
| 49 | 2402.05054 | LGM: Large Multi-View Gaussian Model for High-Resolution 3D Content... | Tang | 2024 | Generative 3D Representations |
| 50 | 2311.06214 | Instant3D: Fast Text-to-3D with Sparse-View Generation and Large Re... | Li | 2023 | Generative 3D Representations |
OSS repository READMEs (Phase 3 mirror targets)
These repositories are referenced in Phase 1 frontmatter (oss_repo: field) and will have READMEs mirrored in Phase 3. They are listed here so the provenance audit is complete from Phase 1 onward.
Permissive licenses (MIT / Apache-2.0 / BSD) allow README redistribution with attribution. The corpus mirrors only the README files, not source code. The non-permissive licenses (Inria / NVIDIA research, custom) ship under research-only terms; including a short README mirror with attribution preserved and no code is treated as fair-use citation, but we flag the non-permissive status here so anyone forking the corpus is informed.
Phase 3 mirror picks (12 repos):
| Repo | License | URL | Justification |
|---|---|---|---|
graphdeco-inria/gaussian-splatting | Gaussian-Splatting License (research-only, non-commercial) (non-permissive — README mirror only) | https://github.com/graphdeco-inria/gaussian-splatting | Canonical 3D Gaussian Splatting reference implementation (Kerbl et al., 2308.04079). |
nerfstudio-project/gsplat | Apache-2.0 | https://github.com/nerfstudio-project/gsplat | Open, permissive CUDA Gaussian splatting library used by Nerfstudio (paper: 2312.02121). |
bmild/nerf | MIT | https://github.com/bmild/nerf | Original NeRF reference implementation (Mildenhall et al., 2003.08934). |
NVlabs/instant-ngp | NVIDIA Source Code License-NC (non-commercial research) (non-permissive — README mirror only) | https://github.com/NVlabs/instant-ngp | Reference instant-NGP implementation (Müller et al., 2201.05989). Era-defining NeRF baseline. |
sxyu/svox2 | BSD-2-Clause | https://github.com/sxyu/svox2 | Plenoxels reference implementation (Yu et al., 2112.05131). |
princeton-vl/DROID-SLAM | BSD-3-Clause | https://github.com/princeton-vl/DROID-SLAM | DROID-SLAM reference implementation (Teed & Deng, 2108.10869). |
Totoro97/NeuS | MIT | https://github.com/Totoro97/NeuS | NeuS reference implementation (Wang et al., 2106.10689). |
cvlab-columbia/zero123 | MIT | https://github.com/cvlab-columbia/zero123 | Zero-1-to-3 reference implementation (Liu et al., 2303.11328). |
ashawkey/stable-dreamfusion | Apache-2.0 | https://github.com/ashawkey/stable-dreamfusion | Widely used open reimplementation of DreamFusion (paper: 2209.14988). |
dreamgaussian/dreamgaussian | MIT | https://github.com/dreamgaussian/dreamgaussian | DreamGaussian reference implementation (Tang et al., 2309.16653). |
VAST-AI-Research/TripoSR | MIT | https://github.com/VAST-AI-Research/TripoSR | TripoSR reference implementation (Tochilkin et al., 2403.02151). |
hustvl/4DGaussians | Apache-2.0 | https://github.com/hustvl/4DGaussians | 4D Gaussian Splatting reference (Wu et al., 2310.08528). |
Additional OSS repos referenced from paper frontmatter (not all of these will have READMEs mirrored — listed here for full audit):
| Repo | License | URL | Justification |
|---|---|---|---|
hbb1/2d-gaussian-splatting | Inria/MPII research license (inherits from upstream 3DGS) (non-permissive) | https://github.com/hbb1/2d-gaussian-splatting | Official 2D Gaussian Splatting implementation (Huang et al., 2403.17888). |
google/mipnerf | Apache-2.0 | https://github.com/google/mipnerf | Reference implementation of Mip-NeRF (Barron et al., 2103.13415). |
sarafridov/K-Planes | BSD-3-Clause | https://github.com/sarafridov/K-Planes | K-Planes reference implementation (Fridovich-Keil et al., 2301.10241). |
muskie82/MonoGS | License notice in repo (research-only) (non-permissive) | https://github.com/muskie82/MonoGS | Gaussian Splatting SLAM official code (Matsuki et al., 2312.06741). |
Anttwo/SuGaR | Custom (research-only, inherits from upstream 3DGS) (non-permissive) | https://github.com/Anttwo/SuGaR | SuGaR reference implementation (Guédon & Lepetit, 2311.12775). |
3DTopia/LGM | MIT | https://github.com/3DTopia/LGM | LGM reference implementation (Tang et al., 2402.05054). |
Internal synthetic content (Phases 4–5)
The following content categories will be authored from scratch by the Tesserae maintainers (Claude-drafted, human-reviewed) and are not mirrored from any external source. They are released under the same license as the rest of the Tesserae repository (see top-level LICENSE).
- Daily digests (
data/research/daily/*/digest.md, 6 files) — fabricated narrative roundups; cite real corpus papers/repos but the prose is original. - Weekly syntheses (
data/research/weekly/*/synthesis.md, 2 files) — original essays synthesizing the digests. - Open questions (
data/research/questions/*.md, 3 files) — original research-gap framings. - Agent session transcripts (
.agent-sessions/*/transcript.jsonl) — fabricated demonstrations of MCP query workflows. Tool names are real (verified againsttesserae/mcp_server.py); the conversation is scripted. - Corpus README (
README.md) — original framing. - Paper bodies (
data/research/papers/<slug>/paper.md, to be added in Phase 2) — original 200–400 word summaries of each paper's claims, NOT paragraph quotes from the paper body. No copyrighted text from the paper PDFs is reproduced.
What's intentionally excluded
- Paper PDFs and full paper bodies (only abstracts, which are CC0 on arXiv).
- Repository source code (only READMEs in Phase 3, license-permitting).
- Author photographs, dataset images, or any media files.
Auditing this corpus
Every paper-abstract file carries license: CC0 (arXiv abstract) in its frontmatter. To verify:
grep -lE '^license: CC0' examples/demo-corpus/data/research/papers/*/abstract.md | wc -l # expect 50