paper-with-me

홈 › Papers

TwinDiffusion: Enhancing Coherence and Efficiency in Panoramic Image Generation with Diffusion Models

2024-04-30 · Teng Zhou, Yongchuan Tang

Diffusion models have emerged as effective tools for generating diverse and high-quality content. However, their capability in high-resolution image generation, particularly for panoramic images, still faces challenges such as visible seams and incoherent transitions. In this paper, we propose TwinDiffusion, an optimized framework designed to address these challenges through two key innovations: the Crop Fusion for quality enhancement and the Cross Sampling for efficiency optimization. We introduce a training-free optimizing stage to refine the similarity of adjacent image areas, as well as an interleaving sampling strategy to yield dynamic patches during the cropping process. A comprehensive evaluation is conducted to compare TwinDiffusion with the prior works, considering factors including coherence, fidelity, compatibility, and efficiency. The results demonstrate the superior performance of our approach in generating seamless and coherent panoramas, setting a new standard in quality and efficiency for panoramic image generation.

📄 PDF Abstract BibTeX arXiv:2404.19475

Code (1)

0606zt/TwinDiffusion 공식 구현 pytorch

Tasks

Image Generation

Similar Papers 제목 키워드 기반

Enhancing In-context Panoramic Generation via Geometric-aware Pretraining

2026-07-09 · Haoran Feng, Ruiyang Zhang, Longyi Zhang, Dizhe Zhang 외 arxiv

In this work, we present Canvas360, a two-stage framework for in-context panoramic generation that combines geometry-aware pretraining with downstream task-specific fine-tuning. To address the lack of large-scale, high-q…

Style Transfer

VGGT-360: Geometry-Consistent Zero-Shot Panoramic Depth Estimation

2026-03-19 · Jiayi Yuan, Haobo Jiang, De Wen Soh, Na Zhao arxiv

This paper presents VGGT-360, a novel training-free framework for zero-shot, geometry-consistent panoramic depth estimation. Unlike prior view-independent training-free approaches, VGGT-360 reformulates the task as panor…

3D ReconstructionDepth Estimation

Veila: Panoramic LiDAR Generation from a Monocular RGB Image

2025-08-05 · Youquan Liu, Lingdong Kong, Weidong Yang, Ao Liang 외 arxiv

Realistic and controllable panoramic LiDAR data generation is critical for scalable 3D perception in autonomous driving and robotics. Existing methods either perform unconditional generation with poor controllability or …

LIDAR Semantic SegmentationAutonomous DrivingData Augmentation

Hallucinating 360°: Panoramic Street-View Generation via Local Scenes Diffusion and Probabilistic Prompting

2025-07-09 · Fei Teng, Kai Luo, Sheng Wu, Siyu Li 외 arxiv

Panoramic perception holds significant potential for autonomous driving, enabling vehicles to acquire a comprehensive 360° surround view in a single shot. However, autonomous driving is a data-driven task. Complete panor…

Image Quality AssessmentAutonomous DrivingImage Generation

Splatter-360: Generalizable 360 Gaussian Splatting for Wide-baseline Panoramic Images

2025-01-01 · CVPR 2025 1 · Zheng Chen, Chenming Wu, Zhelun Shen, Chen Zhao 외

Wide-baseline panoramic images are frequently used in applications like VR and simulations to minimize capturing labor costs and storage needs. However, synthesizing novel views from these panoramic images in real ti…

3DGSNeRF