From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perception and reasoning in VLMs.
☆78Jan 5, 2026Updated last month
Alternatives and similar repositories for SPAR
Users that are interested in SPAR are comparing it to the libraries listed below
Sorting:
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆37Jan 12, 2026Updated last month
- 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration. Accepted to NeurIPS 2025.☆48Jan 10, 2026Updated last month
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆200Jun 4, 2025Updated 8 months ago
- ☆43Jun 3, 2025Updated 8 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆67Jul 22, 2025Updated 7 months ago
- UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding☆60Aug 19, 2025Updated 6 months ago
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆204Nov 28, 2025Updated 3 months ago
- SGDrive: Scene-to-Goal Hierarchical World Cognition for Autonomous Driving☆42Jan 16, 2026Updated last month
- ☆41Jun 9, 2025Updated 8 months ago
- [NeurIPS 2025] Streaming 3D Reconstruction with Explicit Spatial Pointer Memory☆179Sep 26, 2025Updated 5 months ago
- ☆74Mar 29, 2025Updated 11 months ago
- Official implementation of the paper "Unifying 3D Vision-Language Understanding via Promptable Queries"☆84Aug 2, 2024Updated last year
- [ICLR 2025] Diffusion²: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models☆56Mar 18, 2025Updated 11 months ago
- Official repo and evaluation implementation of VSI-Bench☆673Aug 5, 2025Updated 6 months ago
- [ICLR 2025] GS-LiDAR: Generating Realistic LiDAR Point Clouds with Panoramic Gaussian Splatting☆148Mar 18, 2025Updated 11 months ago
- [ICCV 2025] Driving Scene Synthesis on Free-form Trajectories with Generative Prior☆39Jun 28, 2025Updated 8 months ago
- CVPR 2025: VoxelSplat: Dynamic Gaussian Splatting as an Effective Loss for Occupancy and Flow Prediction☆77Aug 1, 2025Updated 6 months ago
- Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"☆278Mar 19, 2025Updated 11 months ago
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆372Oct 21, 2025Updated 4 months ago
- Official code for "Rethinking Chain-of-Thought Reasoning for Videos"☆20Dec 14, 2025Updated 2 months ago
- ☆20Oct 15, 2025Updated 4 months ago
- Official implementation of DepthLM☆311Feb 6, 2026Updated 3 weeks ago
- [AAAI 2024] Mono3DVG: 3D Visual Grounding in Monocular Images, AAAI, 2024☆66Apr 9, 2024Updated last year
- [CVPR 2025] Bridging Past and Future: End-to-End Autonomous Driving with Historical Prediction and Planning☆93Apr 7, 2025Updated 10 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆104Jul 9, 2025Updated 7 months ago
- [ICCV2025] BézierGS: Dynamic Urban Scene Reconstruction with Bézier Curve Gaussian Splatting☆127Sep 3, 2025Updated 5 months ago
- [CVPR 2025] TensoFlow: Tensorial Flow-based Sampler for Inverse Rendering☆15Sep 20, 2025Updated 5 months ago
- ☆22Jun 5, 2025Updated 8 months ago
- ☆13Mar 28, 2025Updated 11 months ago
- [CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆341Updated this week
- Pytorch implementation of Yolo V3☆11Aug 30, 2018Updated 7 years ago
- [CVPR 2024] "LL3DA: Visual Interactive Instruction Tuning for Omni-3D Understanding, Reasoning, and Planning"; an interactive Large Langu…☆311Jul 17, 2024Updated last year
- [ICLR 2023] SQA3D for embodied scene understanding and reasoning☆155Oct 13, 2023Updated 2 years ago
- [ICCV'2025]: GAP: Gaussianize Any Point Clouds with Text Guidance☆53Nov 6, 2025Updated 3 months ago
- ☆56Oct 3, 2024Updated last year
- [ICCV 2025] Nautilus: Locality-aware Autoencoder for Scalable Mesh Generation☆56Jun 25, 2025Updated 8 months ago
- [CVPR 2025] 3D-LLaVA: Towards Generalist 3D LMMs with Omni Superpoint Transformer☆91May 26, 2025Updated 9 months ago
- Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆438Feb 5, 2026Updated 3 weeks ago
- [CVPR 2025] Uni4D: Unifying Visual Foundation Models for 4D Modeling from a Single Video☆220May 25, 2025Updated 9 months ago