Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2601.03252 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914236825862144 |
|---|---|
| author | Yu, Hao Lin, Haotong Wang, Jiawei Li, Jiaxin Wang, Yida Zhang, Xueyang Wang, Yue Zhou, Xiaowei Hu, Ruizhen Peng, Sida |
| author_facet | Yu, Hao Lin, Haotong Wang, Jiawei Li, Jiaxin Wang, Yida Zhang, Xueyang Wang, Yue Zhou, Xiaowei Hu, Ruizhen Peng, Sida |
| contents | Existing depth estimation methods are fundamentally limited to predicting depth on discrete image grids. Such representations restrict their scalability to arbitrary output resolutions and hinder the geometric detail recovery. This paper introduces InfiniDepth, which represents depth as neural implicit fields. Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates, enabling arbitrary-resolution and fine-grained depth estimation. To better assess our method's capabilities, we curate a high-quality 4K synthetic benchmark from five different games, spanning diverse scenes with rich geometric and appearance details. Extensive experiments demonstrate that InfiniDepth achieves state-of-the-art performance on both synthetic and real-world benchmarks across relative and metric depth estimation tasks, particularly excelling in fine-detail regions. It also benefits the task of novel view synthesis under large viewpoint shifts, producing high-quality results with fewer holes and artifacts. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_03252 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields Yu, Hao Lin, Haotong Wang, Jiawei Li, Jiaxin Wang, Yida Zhang, Xueyang Wang, Yue Zhou, Xiaowei Hu, Ruizhen Peng, Sida Computer Vision and Pattern Recognition Existing depth estimation methods are fundamentally limited to predicting depth on discrete image grids. Such representations restrict their scalability to arbitrary output resolutions and hinder the geometric detail recovery. This paper introduces InfiniDepth, which represents depth as neural implicit fields. Through a simple yet effective local implicit decoder, we can query depth at continuous 2D coordinates, enabling arbitrary-resolution and fine-grained depth estimation. To better assess our method's capabilities, we curate a high-quality 4K synthetic benchmark from five different games, spanning diverse scenes with rich geometric and appearance details. Extensive experiments demonstrate that InfiniDepth achieves state-of-the-art performance on both synthetic and real-world benchmarks across relative and metric depth estimation tasks, particularly excelling in fine-detail regions. It also benefits the task of novel view synthesis under large viewpoint shifts, producing high-quality results with fewer holes and artifacts. |
| title | InfiniDepth: Arbitrary-Resolution and Fine-Grained Depth Estimation with Neural Implicit Fields |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.03252 |