Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2507.21960 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908471158374400 |
|---|---|
| author | Ren, Jiahui Xiang, Mochu Zhu, Jiajun Dai, Yuchao |
| author_facet | Ren, Jiahui Xiang, Mochu Zhu, Jiajun Dai, Yuchao |
| contents | Wide-baseline panorama reconstruction has emerged as a highly effective and pivotal approach for not only achieving geometric reconstruction of the surrounding 3D environment, but also generating highly realistic and immersive novel views. Although existing methods have shown remarkable performance across various benchmarks, they are predominantly reliant on accurate pose information. In real-world scenarios, the acquisition of precise pose often requires additional computational resources and is highly susceptible to noise. These limitations hinder the broad applicability and practicality of such methods. In this paper, we present PanoSplatt3R, an unposed wide-baseline panorama reconstruction method. We extend and adapt the foundational reconstruction pretrainings from the perspective domain to the panoramic domain, thus enabling powerful generalization capabilities. To ensure a seamless and efficient domain-transfer process, we introduce RoPE rolling that spans rolled coordinates in rotary positional embeddings across different attention heads, maintaining a minimal modification to RoPE's mechanism, while modeling the horizontal periodicity of panorama images. Comprehensive experiments demonstrate that PanoSplatt3R, even in the absence of pose information, significantly outperforms current state-of-the-art methods. This superiority is evident in both the generation of high-quality novel views and the accuracy of depth estimation, thereby showcasing its great potential for practical applications. Project page: https://npucvr.github.io/PanoSplatt3R |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_21960 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction Ren, Jiahui Xiang, Mochu Zhu, Jiajun Dai, Yuchao Computer Vision and Pattern Recognition Wide-baseline panorama reconstruction has emerged as a highly effective and pivotal approach for not only achieving geometric reconstruction of the surrounding 3D environment, but also generating highly realistic and immersive novel views. Although existing methods have shown remarkable performance across various benchmarks, they are predominantly reliant on accurate pose information. In real-world scenarios, the acquisition of precise pose often requires additional computational resources and is highly susceptible to noise. These limitations hinder the broad applicability and practicality of such methods. In this paper, we present PanoSplatt3R, an unposed wide-baseline panorama reconstruction method. We extend and adapt the foundational reconstruction pretrainings from the perspective domain to the panoramic domain, thus enabling powerful generalization capabilities. To ensure a seamless and efficient domain-transfer process, we introduce RoPE rolling that spans rolled coordinates in rotary positional embeddings across different attention heads, maintaining a minimal modification to RoPE's mechanism, while modeling the horizontal periodicity of panorama images. Comprehensive experiments demonstrate that PanoSplatt3R, even in the absence of pose information, significantly outperforms current state-of-the-art methods. This superiority is evident in both the generation of high-quality novel views and the accuracy of depth estimation, thereby showcasing its great potential for practical applications. Project page: https://npucvr.github.io/PanoSplatt3R |
| title | PanoSplatt3R: Leveraging Perspective Pretraining for Generalized Unposed Wide-Baseline Panorama Reconstruction |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.21960 |