From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perception and reasoning in VLMs.
☆98Oct 23, 2026Updated this week
Alternatives and similar repositories for SPAR
Users that are interested in SPAR are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- [ICLR 2026] UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding☆65Jul 16, 2026Updated 3 months ago
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆260Nov 28, 2025Updated 10 months ago
- 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration. Accepted to NeurIPS 2025.☆59Jan 10, 2026Updated 9 months ago
- [CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆451Jul 15, 2026Updated 3 months ago
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆225Jun 4, 2025Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- Benchmark and training code for MindCube: spatial mental modeling in vision-language models from limited views.☆174Aug 23, 2026Updated 2 months ago
- Reasoning in Space via Grounding in the World (ICLR 2025)☆57Nov 3, 2025Updated 11 months ago
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆40Jan 12, 2026Updated 9 months ago
- [NeurIPS 2025 Spotlight] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆497Feb 5, 2026Updated 8 months ago
- Unifying 2D and 3D Vision-Language Understanding☆135Jul 2, 2026Updated 3 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆112Jul 9, 2025Updated last year
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆392Oct 21, 2025Updated last year
- ☆80Updated this week
- [ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models☆102Jun 9, 2026Updated 4 months ago
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- [ICML 2026] ReVSI: Rebuilding Visual Spatial Intelligence Evaluation for Accurate Assessment of VLM 3D Reasoning☆91Oct 5, 2026Updated 2 weeks ago
- Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"☆291Mar 19, 2025Updated last year
- Official repo and evaluation implementation of VSI-Bench☆752Aug 5, 2025Updated last year
- [ECCV2026] Visual Spatial Tuning☆215Mar 25, 2026Updated 7 months ago
- [ICLR 2026] Official implementation of the paper "📷 On the Generalization Capacities of MLLMs for Spatial Intelligence"☆31Mar 17, 2026Updated 7 months ago
- [CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models☆312May 14, 2026Updated 5 months ago
- ☆22Apr 14, 2026Updated 6 months ago
- [CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning☆361Apr 18, 2026Updated 6 months ago
- [CVPR 2026] Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆179Feb 25, 2026Updated 8 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆55Oct 3, 2024Updated 2 years ago
- [ECCV 2026] Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views☆14Sep 27, 2026Updated 3 weeks ago
- [CVPR 2025] Beacon3D: Object-centric Evaluation for 3D Grounding-QA☆29Nov 25, 2025Updated 11 months ago
- [ICLR 2026] Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining☆35Apr 26, 2026Updated 5 months ago
- Reinforcing Action Policies by Prophesying☆44Aug 7, 2026Updated 2 months ago
- [ICML 2026] MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence☆43May 1, 2026Updated 5 months ago
- [NeurIPS 2024 & TPAMI 2026] Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers☆222Apr 12, 2026Updated 6 months ago
- [ICLR 2026] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence☆109Apr 28, 2026Updated 5 months ago
- Code release for 'Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs' (NeurIPS 2025)☆32Oct 28, 2025Updated 11 months ago
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- [NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding☆83Sep 29, 2025Updated last year
- [ICLR 2023] SQA3D for embodied scene understanding and reasoning☆173Oct 13, 2023Updated 3 years ago
- Code&Data for Grounded 3D-LLM with Referent Tokens☆137Jan 5, 2025Updated last year
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆987Oct 27, 2025Updated 11 months ago
- [CVPR 2026 Highlight] SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence☆92May 28, 2026Updated 4 months ago
- [NeurIPS 2025] 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding☆161Dec 9, 2025Updated 10 months ago
- [NeurIPS'24] This repository is the implementation of "SpatialRGPT: Grounded Spatial Reasoning in Vision Language Models"☆341Dec 14, 2024Updated last year