yilundu/cross_attention_renderer
CVPR 2023: Learning to Render Novel Views from Wide-Baseline Stereo Pairs
This tool helps researchers and visual effects artists generate smooth video transitions or novel viewpoints between two photos taken from significantly different angles. You input two wide-baseline images, and it outputs a video or a series of images that realistically interpolates the space between those two original views. It's designed for anyone working with 3D reconstruction, virtual reality content, or cinematic effects.
152 stars. No commits in the last 6 months.
Use this if you need to create compelling visual narratives or 3D scene understanding from just two disparate images, without complex 3D modeling.
Not ideal if you require real-time rendering for interactive applications or if you only have a single image as input.
Stars
152
Forks
11
Language
Python
License
—
Category
Last pushed
Jan 05, 2024
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/yilundu/cross_attention_renderer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
3DOM-FBK/deep-image-matching
Multiview matching with deep-learning and hand-crafted local features for COLMAP and other SfM...
suhangpro/mvcnn
Multi-view CNN (MVCNN) for shape recognition
zouchuhang/LayoutNet
Torch implementation of our CVPR 18 paper: "LayoutNet: Reconstructing the 3D Room Layout from a...
andyzeng/tsdf-fusion-python
Python code to fuse multiple RGB-D images into a TSDF voxel volume.
andyzeng/tsdf-fusion
Fuse multiple depth frames into a TSDF voxel volume.