Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2604.08626 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866910141719248896 |
|---|---|
| author | Huang, Weikai Zhang, Jieyu Li, Sijun Jia, Taoyang Duan, Jiafei Cheng, Yunqian Cho, Jaemin Wallingford, Matthew Soraki, Rustin Kim, Chris Dongjoo Liu, Shuo Clay, Donovan Anderson, Taira Han, Winson Farhadi, Ali Hariharan, Bharath Ren, Zhongzheng Krishna, Ranjay |
| author_facet | Huang, Weikai Zhang, Jieyu Li, Sijun Jia, Taoyang Duan, Jiafei Cheng, Yunqian Cho, Jaemin Wallingford, Matthew Soraki, Rustin Kim, Chris Dongjoo Liu, Shuo Clay, Donovan Anderson, Taira Han, Winson Farhadi, Ali Hariharan, Bharath Ren, Zhongzheng Krishna, Ranjay |
| contents | Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection--recovering the extent, location, and orientation of objects from an input RGB image. To be practical in the open world, such a detector must generalize beyond closed-set categories, support diverse prompt modalities, and leverage geometric cues when available. Progress is hampered by two bottlenecks: existing methods are designed for a single prompt type and lack a mechanism to incorporate additional geometric cues, and current 3D datasets cover only narrow categories in controlled environments, limiting open-world transfer. In this work we address both gaps. First, we introduce WildDet3D, a unified geometry-aware architecture that natively accepts text, point, and box prompts and can incorporate auxiliary depth signals at inference time. Second, we present WildDet3D-Data, the largest open 3D detection dataset to date, constructed by generating candidate 3D boxes from existing 2D annotations and retaining only human-verified ones, yielding over 1M images across 13.5K categories in diverse real-world scenes. WildDet3D establishes a new state-of-the-art across multiple benchmarks and settings. In the open-world setting, it achieves 22.6/24.8 AP3D on our newly introduced WildDet3D-Bench with text and box prompts. On Omni3D, it reaches 34.2/36.4 AP3D with text and box prompts, respectively. In zero-shot evaluation, it achieves 40.3/48.9 ODS on Argoverse 2 and ScanNet. Notably, incorporating depth cues at inference time yields substantial additional gains (+20.7 AP on average across settings). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_08626 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | WildDet3D: Scaling Promptable 3D Detection in the Wild Huang, Weikai Zhang, Jieyu Li, Sijun Jia, Taoyang Duan, Jiafei Cheng, Yunqian Cho, Jaemin Wallingford, Matthew Soraki, Rustin Kim, Chris Dongjoo Liu, Shuo Clay, Donovan Anderson, Taira Han, Winson Farhadi, Ali Hariharan, Bharath Ren, Zhongzheng Krishna, Ranjay Computer Vision and Pattern Recognition Understanding objects in 3D from a single image is a cornerstone of spatial intelligence. A key step toward this goal is monocular 3D object detection--recovering the extent, location, and orientation of objects from an input RGB image. To be practical in the open world, such a detector must generalize beyond closed-set categories, support diverse prompt modalities, and leverage geometric cues when available. Progress is hampered by two bottlenecks: existing methods are designed for a single prompt type and lack a mechanism to incorporate additional geometric cues, and current 3D datasets cover only narrow categories in controlled environments, limiting open-world transfer. In this work we address both gaps. First, we introduce WildDet3D, a unified geometry-aware architecture that natively accepts text, point, and box prompts and can incorporate auxiliary depth signals at inference time. Second, we present WildDet3D-Data, the largest open 3D detection dataset to date, constructed by generating candidate 3D boxes from existing 2D annotations and retaining only human-verified ones, yielding over 1M images across 13.5K categories in diverse real-world scenes. WildDet3D establishes a new state-of-the-art across multiple benchmarks and settings. In the open-world setting, it achieves 22.6/24.8 AP3D on our newly introduced WildDet3D-Bench with text and box prompts. On Omni3D, it reaches 34.2/36.4 AP3D with text and box prompts, respectively. In zero-shot evaluation, it achieves 40.3/48.9 ODS on Argoverse 2 and ScanNet. Notably, incorporating depth cues at inference time yields substantial additional gains (+20.7 AP on average across settings). |
| title | WildDet3D: Scaling Promptable 3D Detection in the Wild |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.08626 |