Stars
Rebuild the object in a reference image as a code-only, procedural, quality-gated, animation-ready Three.js model. Token-efficient image-to-3D.
CanoVerse: 3D Object Scalable Canonicalization and Dataset for Generation and Pose (ECCV2026)
WorldOlympiad: Can Your World Model Survive a Triathlon?
Latent Spatial Memory for Video World Models
TriSplat: Simulation-Ready Feed-Forward 3D Scene Reconstruction
Code for "SceneSmith: Agentic Generation of Simulation-Ready Indoor Scenes", ICML 2026 Spotlight
Official Pytorch Implementation for "Time-to-Move: Training-Free Motion Controlled Video Generation via Dual-Clock Denoising"
[ICML 2026] World-R1: Reinforcing 3D Constraints for Text-to-Video Generation
[ICLR 2026] NOVA3R: Non-pixel-aligned Visual Transformer for Amodal 3D Reconstruction
An curated list for feed-forward 3D scene modeling, including research directions, datasets, and applications.
Create and share 3D architectural projects.
MegaFlow: Zero-Shot Large Displacement Optical Flow
Official code of Motus: A Unified Latent Action World Model
Equip Claude Code with Nano Banana - image generation & editing via Gemini API
[ECCV'26 Oral] ReSplat: Learning Recurrent Gaussian Splatting
ARIS ⚔️ (Auto-Research-In-Sleep) — Lightweight Markdown-only skills for autonomous ML research: cross-model review loops, idea discovery, and experiment automation. No framework, no lock-in — works…
IronClaw is an Agent OS focused on privacy, security and extensibility
[CVPR'26 Highlight] AMB3R: Accurate Feed-forward Metric-scale 3D Reconstruction with Backend
[CVPR 2026] Official implementation of "MoVieS: Motion-Aware 4D Dynamic View Synthesis in One Second".
A community collection of OpenClaw use cases for making life easier.
[ICLR'26] YoNoSplat: You Only Need One Model for Feedforward 3D Gaussian Splatting
Official implementation of NeurIPS 2025 paper "SceneWeaver: All-in-One 3D Scene Synthesis with an Extensible and Self-Reflective Agent"
PhysX-Anything: Simulation-Ready Physical 3D Assets from Single Image (CVPR 2026)
[ACL 2026 Findings] CoV: Chain-of-View Prompting for Spatial Reasoning
G3Splat: Geometrically Consistent Generalizable Gaussian Splatting
[ECCV 2026] VolSplat: Rethinking Feed-Forward 3D Gaussian Splatting with Voxel-Aligned Prediction
Native and Compact Structured Latents for 3D Generation