basilevh/gcd
Generative Camera Dolly: Extreme Monocular Dynamic Novel View Synthesis (ECCV 2024 Oral) - Official Implementation
This project helps create new video perspectives from a single input video, as if a camera is moving around the scene. You provide an existing video, and it generates new video footage showing the scene from different angles or camera paths. This is useful for filmmakers, marketers, or researchers who need to visualize dynamic scenes from varied viewpoints without re-shooting.
284 stars.
Use this if you need to generate dynamic new camera movements and viewpoints from a single video, giving the impression of a moving camera 'dolly' shot.
Not ideal if you need to edit existing video content or perform static image manipulation; this focuses on generating new views of dynamic scenes.
Stars
284
Forks
9
Language
Python
License
GPL-3.0
Category
Last pushed
Nov 18, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/diffusion/basilevh/gcd"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
PRIS-CV/DemoFusion
Let us democratise high-resolution generation! (CVPR 2024)
mit-han-lab/distrifuser
[CVPR 2024 Highlight] DistriFusion: Distributed Parallel Inference for High-Resolution Diffusion Models
Tencent-Hunyuan/HunyuanPortrait
[CVPR-2025] The official code of HunyuanPortrait: Implicit Condition Control for Enhanced...
giuvecchio/matfuse
MatFuse: Controllable Material Generation with Diffusion Models (CVPR2024)
Shilin-LU/TF-ICON
[ICCV 2023] "TF-ICON: Diffusion-Based Training-Free Cross-Domain Image Composition" (Official...