Video Object Detection
Free video object detection AI tools for identifying and tracking 3D objects in videos, enhancing content creation for films and games.
GVHMR can recover human motion from monocular videos by estimating poses in a Gravity-View coordinate system aligned with gravity and the camera.
VimTS can extract text from images and videos, improving how well it works across different types of media.
FlowSAM can discover and segment moving objects in videos by combining the Segment Anything Model (SAM) with optical flow. It outperforms previous methods, achieving better object identity and sequence-level segmentation for both single and multi-object scenarios.
DSTA is a method for video-based human pose estimation which is able to directly map input to output joint coordinates.
Total-Recon can render scenes from monocular RGBD videos from different camera angles, like first-person and third-person views. It creates realistic 3D videos of moving objects and allows for 3D filters that add virtual items to people in the scene.