PanoTask: Task-Driven Panoramic Video Generation with Scene-Aware Autoregressive Camera Trajectory Prediction
Open Access
- 9 November 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 2731-2739
Abstract
No abstract availableFunding Information
- National Natural Science Foundation of China (62361146854)
- National Natural Science Foundation of China (62372025)
- Joint NSFC-ISF Research Grant (3077\/23)
This publication has 17 references indexed in Scilit:
- RealCam-I2V: Real-World Image-to-Video Generation with Interactive Complex Camera Control2025
- Go-with-the-Flow: Motion-Controllable Video Diffusion Models Using Real-Time Warped Noise2025
- Taming Stable Diffusion for Text to 360° Panorama Image Generation2024
- Spacetime Gaussian Feature Splatting for Real-Time Dynamic View Synthesis2024
- VideoCrafter2: Overcoming Data Limitations for High-Quality Video Diffusion Models2024
- 360DVD: Controllable Panorama Video Generation with 360-Degree Video Diffusion Model2024
- VBench: Comprehensive Benchmark Suite for Video Generative Models2024
- Reproducible Scaling Laws for Contrastive Language-Image Learning2023
- StyleGAN-V: A Continuous Video Generator with the Price, Image Quality and Perks of StyleGAN22022
- 3D-FRONT: 3D Furnished Rooms with layOuts and semaNTics2021