# Sora Generates Videos with Stunning Geometrical Consistency

arXiv: https://arxiv.org/abs/2402.17403 · HTML: https://mlsanity.com/paper/2402.17403/

## Key facts

- Cited by 31 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 19 references that are in the map.
- First posted on arXiv 27 Feb 2024.

## Builds on (most cited first, 8 of 8)

- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [3D Gaussian Splatting for Real-Time Radiance Field Rendering](https://mlsanity.com/paper/2308.04079/) (2023)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets](https://mlsanity.com/paper/2311.15127/) (2023)
- [Video Diffusion Models](https://mlsanity.com/paper/2204.03458/) (2022)
- [Align your Latents: High-Resolution Video Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2304.08818/) (2023)
- [MagicVideo: Efficient Video Generation With Latent Diffusion Models](https://mlsanity.com/paper/2211.11018/) (2022)
- [MaskDiffusion: Boosting Text-to-Image Consistency with Conditional Mask](https://mlsanity.com/paper/2309.04399/) (2023)

## Built on by (most cited first, 30 of 31)

- [VBench-2.0: Advancing Video Generation Benchmark Suite for Intrinsic Faithfulness](https://mlsanity.com/paper/2503.21755/) (2025)
- [MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captions](https://mlsanity.com/paper/2407.06358/) (2024)
- [V3D: Video Diffusion Models are Effective 3D Generators](https://mlsanity.com/paper/2403.06738/) (2024)
- [Geo4D: Leveraging Video Generators for Geometric 4D Scene Reconstruction](https://mlsanity.com/paper/2504.07961/) (2025)
- [Controlling Space and Time with Diffusion Models](https://mlsanity.com/paper/2407.07860/) (2024)
- [Endora: Video Generation Models as Endoscopy Simulators](https://mlsanity.com/paper/2403.11050/) (2024)
- [Infinite-World: Scaling Interactive World Models to 1000-Frame Horizons via Pose-Free Hierarchical Memory](https://mlsanity.com/paper/2602.02393/) (2026)
- [Streetscapes: Large-scale Consistent Street View Generation Using Autoregressive Video Diffusion](https://mlsanity.com/paper/2407.13759/) (2024)
- [FlowR: Flowing from Sparse to Dense 3D Reconstructions](https://mlsanity.com/paper/2504.01647/) (2025)
- [VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Step](https://mlsanity.com/paper/2504.01956/) (2025)
- [Disco4D: Disentangled 4D Human Generation and Animation from a Single Image](https://mlsanity.com/paper/2409.17280/) (2024)
- [Large Physics Models: Towards a collaborative approach with Large Language Models and Foundation Models](https://mlsanity.com/paper/2501.05382/) (2025)
- [Survey of Video Diffusion Models: Foundations, Implementations, and Applications](https://mlsanity.com/paper/2504.16081/) (2025)
- [Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond](https://mlsanity.com/paper/2604.22748/) (2026)
- [LiftImage3D: Lifting Any Single Image to 3D Gaussians with Video Generation Priors](https://mlsanity.com/paper/2412.09597/) (2024)
- [SEED4D: A Synthetic Ego--Exo Dynamic 4D Data Generator, Driving Dataset and Benchmark](https://mlsanity.com/paper/2412.00730/) (2024)
- [UnityVideo: Unified Multi-Modal Multi-Task Learning for Enhancing World-Aware Video Generation](https://mlsanity.com/paper/2512.07831/) (2025)
- [What You See Is What Matters: A Novel Visual and Physics-Based Metric for Evaluating Video Generation Quality](https://mlsanity.com/paper/2411.13609/) (2024)
- [3D-Aware Implicit Motion Control for View-Adaptive Human Video Generation](https://mlsanity.com/paper/2602.03796/) (2026)
- [GaVS: 3D-Grounded Video Stabilization via Temporally-Consistent Local Reconstruction and Rendering](https://mlsanity.com/paper/2506.23957/) (2025)
- [PhyDetEx: Detecting and Explaining the Physical Plausibility of T2V Models](https://mlsanity.com/paper/2512.01843/) (2025)
- [VFMF: World Modeling by Forecasting Vision Foundation Model Features](https://mlsanity.com/paper/2512.11225/) (2025)
- [Kling-MotionControl Technical Report](https://mlsanity.com/paper/2603.03160/) (2026)
- ["Sora is Incredible and Scary": Emerging Governance Challenges of Text-to-Video Generative AI Models](https://mlsanity.com/paper/2406.11859/) (2024)
- [Quality Prediction of AI Generated Images and Videos: Emerging Trends and Opportunities](https://mlsanity.com/paper/2410.08534/) (2024)
- [Mapping the Mind of an Instruction-based Image Editing using SMILE](https://mlsanity.com/paper/2412.16277/) (2024)
- [VideoVerse: Does Your T2V Generator Have World Model Capability to Synthesize Videos?](https://mlsanity.com/paper/2510.08398/) (2025)
- [Measuring 3D Spatial Geometric Consistency in Dynamic Video Generation](https://mlsanity.com/paper/2603.19048/) (2026)
- [GeoT2V-Bench: Benchmarking 3D Consistency in Text-to-Video Models via 3D Reconstruction](https://mlsanity.com/paper/2606.24829/) (2026)
- [RoboPhys-3D: A Comprehensive Embodied World Model Evaluation via 3D Reconstruction](https://mlsanity.com/paper/2608.28718/) (2026)

## 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/