Rundong Luo
@redfairy2002.bsky.social
CS PhD Student @cornelluniversity.bsky.social
5/6 But it doesn't stop there! Our model enables exciting potential applications like video stabilization without cropping, camera viewpoint control, and even interactive visual question answering.
April 23, 2025 at 4:01 PM
5/6 But it doesn't stop there! Our model enables exciting potential applications like video stabilization without cropping, camera viewpoint control, and even interactive visual question answering.
4/6 Our model can predict scene dynamics: We capture a scene with a 360° camera and provide our model with a 60° FoV input of fixed viewing direction (left). The car's ground truth trajectory (middle) and our model's predicted trajectory (right) shows strong alignment.
April 23, 2025 at 4:01 PM
4/6 Our model can predict scene dynamics: We capture a scene with a 360° camera and provide our model with a 60° FoV input of fixed viewing direction (left). The car's ground truth trajectory (middle) and our model's predicted trajectory (right) shows strong alignment.
3/6 Our solution? We've created a high-quality data pipeline leveraging vast online 360° videos, carefully curated to build effective training pairs.
Our model can generate spatially-coherent and temporally-consistent 360° videos from arbitrary in-the-wild perspective inputs.
Our model can generate spatially-coherent and temporally-consistent 360° videos from arbitrary in-the-wild perspective inputs.
April 23, 2025 at 4:00 PM
3/6 Our solution? We've created a high-quality data pipeline leveraging vast online 360° videos, carefully curated to build effective training pairs.
Our model can generate spatially-coherent and temporally-consistent 360° videos from arbitrary in-the-wild perspective inputs.
Our model can generate spatially-coherent and temporally-consistent 360° videos from arbitrary in-the-wild perspective inputs.
2/6 ⬆️Input (left): Standard perspective video from a single viewpoint
Output (right): Our generated 360° panorama created from the input. The red box highlights the corresponding region from the original input.
Output (right): Our generated 360° panorama created from the input. The red box highlights the corresponding region from the original input.
April 23, 2025 at 3:59 PM
2/6 ⬆️Input (left): Standard perspective video from a single viewpoint
Output (right): Our generated 360° panorama created from the input. The red box highlights the corresponding region from the original input.
Output (right): Our generated 360° panorama created from the input. The red box highlights the corresponding region from the original input.
1/6 🔍➡️ How to transform standard videos into immersive 360° panoramas? We've designed a new AI system for video-to-360° panorama generation!
Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.
Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.
April 23, 2025 at 3:49 PM
1/6 🔍➡️ How to transform standard videos into immersive 360° panoramas? We've designed a new AI system for video-to-360° panorama generation!
Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.
Our key insight: large-scale data is crucial for robust panoramic synthesis across diverse scenes.