# 3DSPA: A 3D Semantic Point Autoencoder for Evaluating Video Realism

arXiv: https://arxiv.org/abs/2602.20354 · HTML: https://mlsanity.com/paper/2602.20354/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 31 of its 42 references that are in the map.
- First posted on arXiv 23 Feb 2026.

## Builds on (most cited first, 30 of 31)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Qwen2.5-VL Technical Report](https://mlsanity.com/paper/2502.13923/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context](https://mlsanity.com/paper/2403.05530/) (2024)
- [VBench: Comprehensive Benchmark Suite for Video Generative Models](https://mlsanity.com/paper/2311.17982/) (2023)
- [Towards Accurate Generative Models of Video: A New Metric & Challenges](https://mlsanity.com/paper/1812.01717/) (2018)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Cosmos World Foundation Model Platform for Physical AI](https://mlsanity.com/paper/2501.03575/) (2025)
- [V-JEPA 2: Self-Supervised Video Models Enable Understanding, Prediction and Planning](https://mlsanity.com/paper/2506.09985/) (2025)
- [Revisiting Feature Prediction for Learning Visual Representations from Video](https://mlsanity.com/paper/2404.08471/) (2024)
- [VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://mlsanity.com/paper/2303.16727/) (2023)
- [Kubric: A scalable dataset generator](https://mlsanity.com/paper/2203.03570/) (2022)
- [Unleashing Large-Scale Video Generative Pre-training for Visual Robot Manipulation](https://mlsanity.com/paper/2312.13139/) (2023)
- [EvalCrafter: Benchmarking and Evaluating Large Video Generation Models](https://mlsanity.com/paper/2310.11440/) (2023)
- [Pros and Cons of GAN Evaluation Measures](https://mlsanity.com/paper/1802.03446/) (2018)
- [Video Depth Anything: Consistent Depth Estimation for Super-Long Videos](https://mlsanity.com/paper/2501.12375/) (2025)
- [SpatialTracker: Tracking Any 2D Pixels in 3D Space](https://mlsanity.com/paper/2404.04319/) (2024)
- [Do generative video models understand physical principles?](https://mlsanity.com/paper/2501.09038/) (2025)
- [VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generation](https://mlsanity.com/paper/2503.06800/) (2025)
- [DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark](https://mlsanity.com/paper/2405.19707/) (2024)
- [SpatialTrackerV2: 3D Point Tracking Made Easy](https://mlsanity.com/paper/2507.12462/) (2025)
- [TAPVid-3D: A Benchmark for Tracking Any Point in 3D](https://mlsanity.com/paper/2407.05921/) (2024)
- [IntPhys 2: Benchmarking Intuitive Physics Understanding In Complex Synthetic Environments](https://mlsanity.com/paper/2506.09849/) (2025)
- [Learning Video Generation for Robotic Manipulation with Collaborative Trajectory Control](https://mlsanity.com/paper/2506.01943/) (2025)
- [D3: Training-Free AI-Generated Video Detection Using Second-Order Features](https://mlsanity.com/paper/2508.00701/) (2025)
- [TRAVL: A Recipe for Making Video-Language Models Better Judges of Physics Implausibility](https://mlsanity.com/paper/2510.07550/) (2025)
- [ORV: 4D Occupancy-centric Robot Video Generation](https://mlsanity.com/paper/2506.03079/) (2025)
- [A Physical Coherence Benchmark for Evaluating Video Generation Models via Optical Flow-guided Frame Prediction](https://mlsanity.com/paper/2502.05503/) (2025)

## Abstract (arXiv)

AI video generation is evolving rapidly. For video generators to be useful for applications ranging from robotics to film-making, they must consistently produce realistic videos. However, evaluating the realism of generated videos remains a largely manual process -- requiring human annotation or bespoke evaluation datasets which have restricted scope. Here we develop an automated evaluation framework for video realism which captures both semantics and coherent 3D structure and which does not require access to a reference video. Our method, 3DSPA, is a 3D spatiotemporal point autoencoder which integrates 3D point trajectories, depth cues, and DINO semantic features into a unified representation for video evaluation. 3DSPA models how objects move and what is happening in the scene, enabling robust assessments of realism, temporal consistency, and physical plausibility. Experiments show that 3DSPA reliably identifies videos which violate physical laws, is more sensitive to motion artifacts, and aligns more closely with human judgments of video quality and realism across multiple datasets. Our results demonstrate that enriching trajectory-based representations with 3D semantics offers a stronger foundation for benchmarking generative video models, and implicitly captures physical rule violations. The code and pretrained model weights will be available at https://github.com/TheProParadox/3dspa_code.