monocular videos
Monocular videos are videos captured using a single camera. In AI, processing monocular video data is a challenge as it requires the extraction of depth and spatial information from two-dimensional images for tasks like object detection and segmentation.
- 4D3R: Motion-Aware Neural Reconstruction and Rendering of Dynamic Scenes from Monocular Videos
- Dynamic View Synthesis as an Inverse Problem
- DynamicVerse: A Physically-Aware Multimodal Framework for 4D World Modeling
- Orientation-anchored Hyper-Gaussian for 4D Reconstruction from Casual Videos
- Reconstruct, Inpaint, Test-Time Finetune: Dynamic Novel-view Synthesis from Monocular Videos
- Track3R: Joint Point Map and Trajectory Prior for Spatiotemporal 3D Understanding