mlsanityData to 7 Oct 2026

GeCo: Evaluating Geometric Consistency for Video Generation via Motion and Structure

arXiv 2512.22274 ↗First posted 25 Dec 2025cs.CVcited by 1

Not on the map. Why?

Abstract (arXiv)

We introduce GeCo, a geometry-grounded metric for jointly detecting geometric deformation and occlusion-inconsistency artifacts in static scenes. By fusing residual motion and depth priors, GeCo produces interpretable, dense consistency maps that reveal these artifacts. We use GeCo to systematically benchmark recent video generation models, uncovering common failure modes, and further employ it as a training-free guidance loss to reduce deformation artifacts during video generation.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 50 of its 60 references that are in the map. First posted on arXiv 25 Dec 2025.

Builds on

50 of 60 references.

References · 50

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2021Emerging Properties in Self-Supervised Vision Transformerscited by 6,893
  3. 2023Adding Conditional Control to Text-to-Image Diffusion Modelscited by 5,466
  4. 2017ScanNet: Richly-annotated 3D Reconstructions of Indoor Scenescited by 3,088
  5. 2024SAM 2: Segment Anything in Images and Videoscited by 2,784
  6. 2025Wan: Open and Advanced Large-Scale Video Generative Modelscited by 2,536
  7. 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,198
  8. 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,755
  9. 2024HunyuanVideo: A Systematic Framework For Large Video Generative Modelscited by 1,597
  10. 2023DUSt3R: Geometric 3D Vision Made Easycited by 1,526
  11. 2025VGGT: Visual Geometry Grounded Transformercited by 1,475
  12. 2022RePaint: Inpainting using Denoising Diffusion Probabilistic Modelscited by 1,419
38 more
  1. 2024Depth Anything V2cited by 1,385
  2. 2017SuperPoint: Self-Supervised Interest Point Detection and Descriptioncited by 1,313
  3. 2022CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformerscited by 973
  4. 2025Cosmos World Foundation Model Platform for Physical AIcited by 833
  5. 2023ScanNet++: A High-Fidelity Dataset of 3D Indoor Scenescited by 747
  6. 2021DROID-SLAM: Deep Visual SLAM for Monocular, Stereo, and RGB-D Camerascited by 673
  7. 2021Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstructioncited by 646
  8. 2023ZoeDepth: Zero-shot Transfer by Combining Relative and Metric Depthcited by 646
  9. 2023LightGlue: Local Feature Matching at Light Speedcited by 583
  10. 2022Zero-Shot Image Restoration Using Denoising Diffusion Null-Space Modelcited by 574
  11. 2024LTX-Video: Realtime Video Latent Diffusioncited by 549
  12. 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 514
  13. 2020TartanAir: A Dataset to Push the Limits of Visual SLAMcited by 494
  14. 2023Universal Guidance for Diffusion Modelscited by 426
  15. 2024SV3D: Novel Multi-view Synthesis and 3D Generation from a Single Image using Latent Video Diffusioncited by 364
  16. 2023EvalCrafter: Benchmarking and Evaluating Large Video Generation Modelscited by 332
  17. 2025GEN3C: 3D-Informed World-Consistent Video Generation with Precise Camera Controlcited by 325
  18. 2023ControlVideo: Training-free Controllable Text-to-Video Generationcited by 324
  19. 2025Matrix-game 2.0: An open-source real-time and streaming interactive world modelcited by 174
  20. 2024Towards World Simulator: Crafting Physical Commonsense-Based Benchmark for Video Generationcited by 167
  21. 2023Manifold Preserving Guided Diffusioncited by 153
  22. 2025WorldPlay: Towards Long-Term Geometric Consistency for Real-Time Interactive World Modelingcited by 152
  23. 2025WorldScore: A Unified Evaluation Benchmark for World Generationcited by 143
  24. 2025VideoPhy-2: A Challenging Action-Centric Physical Commonsense Evaluation in Video Generationcited by 141
  25. 2025MEt3R: Measuring Multi-View Consistency in Generated Imagescited by 91
  26. 2025RELIC: Interactive Video World Model with Long-Horizon Memorycited by 89
  27. 2024PhyT2V: LLM-Guided Iterative Self-Refinement for Physics-Grounded Text-to-Video Generationcited by 77
  28. 2023Long-Term Photometric Consistent Novel View Synthesis with Diffusion Modelscited by 76
  29. 2024World-consistent Video Diffusion with Explicit 3D Modelingcited by 62
  30. 2024VFusion3D: Learning Scalable 3D Generative Models from Video Diffusion Modelscited by 56
  31. 2024Motion Guidance: Diffusion-Based Image Editing with Differentiable Motion Estimatorscited by 39
  32. 2025UFM: A Simple Path towards Unified Dense Correspondence with Flowcited by 35
  33. 2025Segment Any Motion in Videoscited by 34
  34. 2025VideoScene: Distilling Video Diffusion Model to Generate 3D Scenes in One Stepcited by 27
  35. 2024Optical-Flow Guided Prompt Optimization for Coherent Video Generationcited by 17
  36. 2025Frame Guidance: Training-Free Guidance for Frame-Level Control in Video Diffusion Modelscited by 11
  37. 2025JOG3R: Towards 3D-Consistent Video Generatorscited by 8
  38. 2024Multistable Shape from Shading Emerges from Patch Diffusioncited by 5

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.