RealCam-Vid: High-resolution Video Dataset with Dynamic Scenes and Metric-scale Camera Movements
Not on the map. Why?
Abstract (arXiv)
Recent advances in camera-controllable video generation have been constrained by the reliance on static-scene datasets with relative-scale camera annotations, such as RealEstate10K. While these datasets enable basic viewpoint control, they fail to capture dynamic scene interactions and lack metric-scale geometric consistency-critical for synthesizing realistic object motions and precise camera trajectories in complex environments. To bridge this gap, we introduce the first fully open-source, high-resolution dynamic-scene dataset with metric-scale camera annotations in https://github.com/ZGCTroy/RealCam-Vid.
Key facts. Cited by 14 papers in the map (data through 14 Oct 2026). Builds on 11 of its 14 references that are in the map. First posted on arXiv 11 Apr 2025.
Builds on
11 of 14 references.
References · 11
- 2024SAM 2: Segment Anything in Images and Videoscited by 2,863
- 2020RAFT: Recurrent All-Pairs Field Transforms for Optical Flowcited by 2,415
- 2024CogVideoX: Text-to-Video Diffusion Models with An Expert Transformercited by 2,261
- 2023VBench: Comprehensive Benchmark Suite for Video Generative Modelscited by 1,822
- 2023PixArt-α: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesiscited by 864
- 2023DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Visioncited by 537
- 2023CoTracker: It is Better to Track Togethercited by 522
- 2024MonST3R: A Simple Approach for Estimating Geometry in the Presence of Motioncited by 442
- 2024Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimationcited by 395
- 2024MiraData: A Large-Scale Video Dataset with Long Durations and Structured Captionscited by 146
- 2024Koala-36M: A Large-scale Video Dataset Improving Consistency between Fine-grained Conditions and Video Contentcited by 135
Built on by
Citing papers per year: 2025: 4; 2026: 10.
14 papers.
Sort:
By area:
- 2025Epipolar Geometry Improves Video Generation Modelscited by 26
- 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformerscited by 14
- 2026SolarWM: Open Data and Scalable Training for Long-Horizon Video World Modelscited by 12
- 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modelingcited by 5
- 2026CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generationcited by 4
- 2026CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warpingcited by 4
- 2026Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Trackscited by 2
- 2026Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rolloutcited by 2
- 2025Tiger200K: Manually Curated High Visual Quality Video Dataset from UGC Platformcited by 1
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spacescited by 1
- 2026FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generationcited by 0
- 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Modelscited by 0
- 20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling13 Oct 2026
- 2026GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models9 Oct 2026
- 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Models8 Oct 2026
- 2026Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout8 Sep 2026
- 2026SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models2 Sep 2026
- 2026FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation23 Jun 2026
- 2026Track2View: 4D-Consistent Camera-Controlled Video Generation via Paired 3D Point Tracks14 Jun 2026
- 2026CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping29 May 2026
- 2026CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation13 May 2026
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces30 Apr 2026
- 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling2 Dec 2025
- 2025Epipolar Geometry Improves Video Generation Models24 Oct 2025
- 2026SolarWM: Open Data and Scalable Training for Long-Horizon Video World Modelscited by 12
- 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modelingcited by 5
- 2026CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generationcited by 4
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spacescited by 1
- 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Modelscited by 0
- 2026GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Modelscited by 0
- 20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modelingcited by 0
- 20264LC: 4D Latent Cache for Efficient Conditioning in Dynamic World Modeling13 Oct 2026
- 2026GLIMPSE: Global-Local Indexing with Multi-Precision Spectral Encoding for Explorable Video World Models9 Oct 2026
- 2026Learning to Retrieve: Internalizing Memory Retrieval for Video World Models8 Oct 2026
- 2026SolarWM: Open Data and Scalable Training for Long-Horizon Video World Models2 Sep 2026
- 2026CRePE: Curved Ray Expectation Positional Encoding for Unified-Camera-Controlled Video Generation13 May 2026
- 2026Beyond Gaussian Bottlenecks: Topologically Aligned Encoding of Vision-Transformer Feature Spaces30 Apr 2026
- 2025DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling2 Dec 2025
- 2025Epipolar Geometry Improves Video Generation Modelscited by 26
- 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformerscited by 14
- 2026CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warpingcited by 4
- 2026Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rolloutcited by 2
- 2026FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generationcited by 0
- 2026Mask Forcing: Improving Autoregressive Video Diffusion Distillation via Dual-Noise Masking Rollout8 Sep 2026
- 2026FLAT: Feedforward Latent Triangle Splatting for Geometrically Accurate Scene Generation23 Jun 2026
- 2026CameraNoise: Enabling Faithful Camera Control in Video Diffusion through Geometry-Flow-Guided Noise Warping29 May 2026
- 2025Epipolar Geometry Improves Video Generation Models24 Oct 2025
- 2025RoPECraft: Training-Free Motion Transfer with Trajectory-Guided RoPE Optimization on Diffusion Transformers19 May 2025