Pay Attention to Where You Looked
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912926866079744 |
|---|---|
| author | Berian, Alex Wu, JhihYang Brignac, Daniel Daba, Natnael Mahalanobis, Abhijit |
| author_facet | Berian, Alex Wu, JhihYang Brignac, Daniel Daba, Natnael Mahalanobis, Abhijit |
| contents | Novel view synthesis (NVS) has advanced with generative modeling, enabling photorealistic image generation. In few-shot NVS, where only a few input views are available, existing methods often assume equal importance for all input views relative to the target, leading to suboptimal results.
We address this limitation by introducing a camera-weighting mechanism that adjusts the importance of source views based on their relevance to the target. We propose two approaches: a deterministic weighting scheme leveraging geometric properties like Euclidean distance and angular differences, and a cross-attention-based learning scheme that optimizes view weighting. Additionally, models can be further trained with our camera-weighting scheme to refine their understanding of view relevance and enhance synthesis quality. This mechanism is adaptable and can be integrated into various NVS algorithms, improving their ability to synthesize high-quality novel views. Our results demonstrate that adaptive view weighting enhances accuracy and realism, offering a promising direction for improving NVS. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_18970 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Pay Attention to Where You Looked Berian, Alex Wu, JhihYang Brignac, Daniel Daba, Natnael Mahalanobis, Abhijit Computer Vision and Pattern Recognition Novel view synthesis (NVS) has advanced with generative modeling, enabling photorealistic image generation. In few-shot NVS, where only a few input views are available, existing methods often assume equal importance for all input views relative to the target, leading to suboptimal results. We address this limitation by introducing a camera-weighting mechanism that adjusts the importance of source views based on their relevance to the target. We propose two approaches: a deterministic weighting scheme leveraging geometric properties like Euclidean distance and angular differences, and a cross-attention-based learning scheme that optimizes view weighting. Additionally, models can be further trained with our camera-weighting scheme to refine their understanding of view relevance and enhance synthesis quality. This mechanism is adaptable and can be integrated into various NVS algorithms, improving their ability to synthesize high-quality novel views. Our results demonstrate that adaptive view weighting enhances accuracy and realism, offering a promising direction for improving NVS. |
| title | Pay Attention to Where You Looked |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.18970 |