From Flatland to Space (SPAR). Accepted to NeurIPS 2025 Datasets & Benchmarks. A large-scale dataset & benchmark for 3D spatial perception and reasoning in VLMs.
☆90Jan 5, 2026Updated 6 months ago
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:
- UniUGG: Unified 3D Understanding and Generation via Geometric-Semantic Encoding. Accepted to ICLR 2026.☆63Updated this week
- [CVPR 2025] The code for paper ''Video-3D LLM: Learning Position-Aware Video Representation for 3D Scene Understanding''.☆218Jun 4, 2025Updated last year
- The code for paper 'Learning from Videos for 3D World: Enhancing MLLMs with 3D Vision Geometry Priors'☆245Nov 28, 2025Updated 7 months ago
- 4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration. Accepted to NeurIPS 2025.☆57Jan 10, 2026Updated 6 months ago
- [CVPR 2026] VLM-3R: Vision-Language Models Augmented with Instruction-Aligned 3D Reconstruction☆428Updated this week
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- ☆163Mar 23, 2026Updated 3 months ago
- Reasoning in Space via Grounding in the World (ICLR 2025)☆56Nov 3, 2025Updated 8 months ago
- STI-Bench : Are MLLMs Ready for Precise Spatial-Temporal World Understanding?☆39Jan 12, 2026Updated 6 months ago
- [NeurIPS 2025 Spotlight] Official implementation of Spatial-MLLM: Boosting MLLM Capabilities in Visual-based Spatial Intelligence☆479Feb 5, 2026Updated 5 months ago
- SpaceR: The first MLLM empowered by SG-RLVR for video spatial reasoning☆111Jul 9, 2025Updated last year
- [ICCV 2025] A Simple yet Effective Pathway to Empowering LLaVA to Understand and Interact with 3D World☆384Oct 21, 2025Updated 8 months ago
- ☆55Oct 3, 2024Updated last year
- [ICLR 2026] Disentangled Robot Learning via Separate Forward and Inverse Dynamics Pretraining☆30Apr 26, 2026Updated 2 months ago
- ☆22Apr 14, 2026Updated 3 months ago
- End-to-end encrypted cloud storage - Proton Drive • AdSpecial offer: 40% Off Yearly / 80% Off First Month. Protect your most important files, photos, and documents from prying eyes.
- [CVPR 2026] Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models☆178Feb 25, 2026Updated 4 months ago
- [ECCV2026] Visual Spatial Tuning☆198Mar 25, 2026Updated 3 months ago
- [CVPR 2025] Beacon3D: Object-centric Evaluation for 3D Grounding-QA☆28Nov 25, 2025Updated 7 months ago
- [CVPR 2026] Scaling Spatial Intelligence with Multimodal Foundation Models☆289May 14, 2026Updated 2 months ago
- [ICLR 2026] SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models☆99Jun 9, 2026Updated last month
- [CVPR 2026 Highlight] SpatialScore: Towards Comprehensive Evaluation for Spatial Intelligence☆84May 28, 2026Updated last month
- [NeurIPS 2025] OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding☆79Sep 29, 2025Updated 9 months ago
- Reinforcing Action Policies by Prophesying☆42Nov 26, 2025Updated 7 months ago
- [ICCV'25] Ross3D: Reconstructive Visual Instruction Tuning with 3D-Awareness☆70Jul 22, 2025Updated 11 months ago
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- [CVPR 2026] G2VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning☆345Apr 18, 2026Updated 3 months ago
- Code release for 'Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs' (NeurIPS 2025)☆31Oct 28, 2025Updated 8 months ago
- Official implementation of ECCV24 paper "SceneVerse: Scaling 3D Vision-Language Learning for Grounded Scene Understanding"☆287Mar 19, 2025Updated last year
- [CVPR 2026] Think with 3D: Geometric Imagination Grounded Spatial Reasoning from Limited Views☆243May 7, 2026Updated 2 months ago
- [ICLR 2026] Streaming 4D Visual Geometry Transformer☆941Oct 27, 2025Updated 8 months ago
- [NeurIPS 2024 & TPAMI 2026] Chat-Scene: Bridging 3D Scene and Large Language Models with Object Identifiers☆216Apr 12, 2026Updated 3 months ago
- [NeurIPS 2025] 3DRS: MLLMs Need 3D-Aware Representation Supervision for Scene Understanding☆158Dec 9, 2025Updated 7 months ago
- ☆68Feb 12, 2026Updated 5 months ago
- Official implementation of the paper "Unifying 3D Vision-Language Understanding via Promptable Queries"☆85Aug 2, 2024Updated last year
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- A benchmark that focuses on the sampling dilemma in long-video tasks. Through well-designed tasks, it evaluates the sampling efficiency o…☆28Aug 7, 2025Updated 11 months ago
- [ICLR 2023] SQA3D for embodied scene understanding and reasoning☆168Oct 13, 2023Updated 2 years ago
- ☆15Jun 19, 2026Updated last month
- [ICLR 2025] Diffusion²: Dynamic 3D Content Generation via Score Composition of Video and Multi-view Diffusion Models☆60Mar 18, 2025Updated last year
- Seeing from Another Perspective: Evaluating Multi-View Understanding in MLLMs☆69Mar 22, 2026Updated 3 months ago
- Official code for paper: N3D-VLM: Native 3D Grounding Enables Accurate Spatial Reasoning in Vision-Language Models☆116Jan 14, 2026Updated 6 months ago
- [ICLR 2026] MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence☆103Apr 28, 2026Updated 2 months ago