mlsanityData to 7 Oct 2026

Sora Generates Videos with Stunning Geometrical Consistency

arXiv 2402.17403 ↗First posted 27 Feb 2024cs.CVcited by 31

Not on the map. Why?

Abstract (arXiv)

The recently developed Sora model [1] has exhibited remarkable capabilities in video generation, sparking intense discussions regarding its ability to simulate real-world phenomena. Despite its growing popularity, there is a lack of established metrics to evaluate its fidelity to real-world physics quantitatively. In this paper, we introduce a new benchmark that assesses the quality of the generated videos based on their adherence to real-world physics principles. We employ a method that transforms the generated videos into 3D models, leveraging the premise that the accuracy of 3D reconstruction is heavily contingent on the video quality. From the perspective of 3D reconstruction, we use the fidelity of the geometric constraints satisfied by the constructed 3D models as a proxy to gauge the extent to which the generated videos conform to real-world physics rules. Project page: https://sora-geometrical-consistency.github.io/

Key facts. Cited by 31 papers in the map (data through 7 Oct 2026). Builds on 8 of its 19 references that are in the map. First posted on arXiv 27 Feb 2024.

Builds on

8 of 19 references.

References · 8

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 20233D Gaussian Splatting for Real-Time Radiance Field Renderingcited by 6,141
  3. 2016Improved Techniques for Training GANscited by 2,938
  4. 2023Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasetscited by 2,526
  5. 2022Video Diffusion Modelscited by 2,280
  6. 2023Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Modelscited by 1,465
  7. 2022MagicVideo: Efficient Video Generation With Latent Diffusion Modelscited by 463
  8. 2023MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Maskcited by 17

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 12; 2025: 11; 2026: 8.

31 papers.

Sort:

By area:

  1. 2025VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulnesscited by 289
  2. 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 144
  3. 2024V3D: Video Diffusion Models are Effective 3D Generatorscited by 88
  4. 2025Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstructioncited by 66
  5. 2024Controlling Space and Time with Diffusion Modelscited by 65
  6. 2024Endora: Video Generation Models as Endoscopy Simulatorscited by 53
  7. 2024Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusioncited by 39
  8. 2026Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memorycited by 37
  9. 2025FlowR: Flowing from Sparse to Dense 3D Reconstructionscited by 28
  10. 2025VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Stepcited by 27
  11. 2024Disco4D: Disentangled 4D Human Generation and Animation from a Single Imagecited by 17
  12. 2025Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Modelscited by 14
19 more
  1. 2025Survey of Video Diffusion Models: Foundations, Implementations, and Applicationscited by 14
  2. 2024LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priorscited by 11
  3. 2026Agentic World Modeling: Foundations, Capabilities, Laws, and Beyondcited by 10
  4. 2024SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmarkcited by 8
  5. 2025UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generationcited by 7
  6. 2024What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Qualitycited by 6
  7. 20263D-Aware Implicit Motion Control for View-Adaptive Human Video Generationcited by 6
  8. 2025GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Renderingcited by 5
  9. 2025VFMF: World Modeling by Forecasting Vision Foundation Model Featurescited by 5
  10. 2025PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Modelscited by 4
  11. 2024"Sora is Incredible and Scary": Emerging Governance Challenges of Text-to-Video Generative AI Modelscited by 3
  12. 2024Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunitiescited by 3
  13. 2024Mapping the Mind of an Instruction-based Image Editing using SMILEcited by 3
  14. 2026Kling-MotionControl Technical Reportcited by 3
  15. 2025VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?cited by 2
  16. 2026Measuring 3D Spatial Geometric Consistency in Dynamic Video Generationcited by 1
  17. 2026GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstructioncited by 1
  18. 2026RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstructioncited by 1
  19. 2026Generating HDR Video from SDR Videocited by 0