zhangquanchen / 3DThinkerLinks
Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views
β107Updated last week
Alternatives and similar repositories for 3DThinker
Users that are interested in 3DThinker are comparing it to the libraries listed below
Sorting:
- [AAAI 2026 π₯] Official implementation of "NeuralGS: Bridging Neural Fields and 3D Gaussian Splatting for Compact 3D Representation"β174Updated 4 months ago
- β140Updated 8 months ago
- 4DNeX: Feed-Forward 4D Generative Modeling Made Easyβ801Updated last week
- [CVPR2024] Instruct 4D-to-4D: Editing 4D Scenes as Pseudo-3D Scenes Using 2D Diffusionβ135Updated last year
- [NeurIPS 2025 Spotlight] Towards Understanding Camera Motions in Any Videoβ250Updated 3 weeks ago
- [Tech Report] Few-Step Distillation for Text-to-Image Generation: A Practical Guideβ132Updated this week
- β74Updated 9 months ago
- [ICCV 2025 Highlight] DIMO: Diverse 3D Motion Generation for Arbitrary Objectsβ134Updated last month
- This is the repository that contains source code for the PhysGen3D.β233Updated 3 months ago
- [NeurIPS 2025 Spotlight] A Native Multimodal LLM for 3D Generation and Understandingβ515Updated 2 months ago
- A Unified Driving World Model for Future Generation and Perceptionβ127Updated 4 months ago
- [ICRA 2025] PUGS: Zero-shot Physical Understanding with Gaussian Splatting.β102Updated 9 months ago
- The official PyTorch implementation of Diffusion Time-step Curriculum for One Image to 3D Generation (CVPR 2024)β74Updated last year
- Official Implementation of Puzzles: Unbounded Video-Depth Augmentation for Scalable, End-to-End 3D Reconstruction.β209Updated 3 months ago
- π WorldLens: Full-Spectrum Evaluations of Driving World Models in Real Worldβ133Updated this week
- [ICLR 2025] This is official implements of Swift4d: Adaptive divide-and-conquer Gaussian Splatting for compact and efficient reconstructiβ¦β144Updated this week
- Wan2.1 with Controlnetβ178Updated 8 months ago
- [NeurIPS 25] TrackingWorld: World-centric Monocular 3D Tracking of Almost All Pixelsβ106Updated this week
- GigaWorld-0: World Models as Data Engine to Empower Embodied AIβ717Updated 2 weeks ago
- [NeurIPS 2025 DB Track] 3EED: Ground Everything Everywhere in 3Dβ193Updated last week
- G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoningβ226Updated 3 weeks ago
- A simple, unified multimodal models training engine. Lean, flexible, and built for hacking at scale.β678Updated last week
- [ICCV2025 Highlight] Stereo Any Video: Temporally Consistent Stereo Matchingβ377Updated 2 weeks ago
- Official implementation of "JavisDiT: Joint Audio-Video Diffusion Transformer with Hierarchical Spatio-Temporal Prior Synchronization"β302Updated 2 weeks ago
- [ICLR 2025] Ctrl-U: Robust Conditional Image Generation via Uncertainty-aware Reward Modelingβ82Updated 10 months ago
- Are Video Models Ready as Zero-shot Reasoners?β84Updated 3 weeks ago
- Identity-GRPO: Optimizing Multi-Human Identity-preserving Video Generation via Reinforcement Learningβ167Updated 2 months ago
- [SIGGRAPH Conference 2024] GaussianPrediction: Dynamic 3D Gaussian Prediction for Motion Extrapolation and Free View Synthesisβ155Updated 8 months ago
- GigaBrain-0: A World Model-Powered Vision-Language-Action Modelβ831Updated 3 weeks ago
- World Simulator Assistant for Physics-Aware Text-to-Video Generationβ254Updated 2 months ago