A.Robot
7.7K posts
@100PercentRobot
One man production studio • Creative technology 25y • Autonomous AF • FOS life • ML Research • Post-Prompt AI powered content
It's live! Alpha 1.0 is on Github. Link below
has generative ai improved literally anything in our lives
just a friendly reminder that if an AI generated it, you didn't make it 🥰
I'll reply to this again for the last time as it annoys me seeing this take. Art only is possible when the tool used does not directly affect the output with "it's own" decisions.
@UltraTerm And yet it still can't duplicate what the prompter actually envisions, or really get anywhere near as close as an artist can in their medium
🚀🚀 Introducing Pixal3D (SIGGRAPH’26) — a new pixel-aligned image-to-3D generation paradigm for high-fidelity 3D asset creation. Today’s Image-to-3D has become pretty good at producing plausible 3D assets. But plausibility is not enough. Fidelity is a hidden bottleneck. ❓A generated model may look “about right,” yet still fail to truly align with the input pixels. Can we make 3D generation as faithful as reconstruction, while still allowing it to complete the unseen? Pixal3D is our answer. 💡We believe the core bottleneck behind fidelity is 2D–3D correspondence. Most 3D-native generators synthesize shapes in canonical space and inject image cues through cross-attention, forcing the model to implicitly search for which pixels correspond to which 3D regions. 🍀Pixal3D takes a different route. Instead of generating in canonical space, Pixal3D generates directly in pixel-aligned camera space — what you see is what you get. The generated 3D asset is aligned with the input view from the start. ☕️Meanwhile, Pixal3D introduces back-projection-based image condition scheme - explicitly back-projects multi-scale pixel features into 3D voxels, thus resolving the 2D-3D association problem. The input image is no longer just a prompt - it becomes a geometric anchor. 🚩Pixal3D shows that pixel-aligned 3D generation is not only feasible and scalable, but also significantly improves fidelity, pushing 3D-native generation closer to reconstruction-level faithfulness. It also naturally extends to multi-view and scene-level 3D generation. ✅Faithful to the input view. ✅Generative for the unseen. Closer to reconstruction-level fidelity, with the creativity of 3D generation. Pixal3D also represents an effort towards the unification of 3D generation and reconstruction. 📢Paper, code, and demo are fully released — try it out and let us know your feedback! 🌐Project page: ldyang694.github.io/projects/pixal… 🤗Huggingface Demo: huggingface.co/spaces/Tencent… 💻Code: github.com/TencentARC/Pix… 📄Paper: arxiv.org/abs/2605.10922
Well, hypothetically. They develop a commercially successful product, which is an important distinction. Anyone can buy the product, my ai agent does. It reviews the content, and finds refs that aren’t paid for. An offer is sent to the successful developer on behalf of the artist(s), requesting compensation. If ignored, any legal channels available will be pursued, automatically. This is a sketch. Ideally, artist networks that produce real art will completely private. In the long term, distribution networks will handle this automatically. Do you honestly think the internet as it exists today benefits artists and creators?
