SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation
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_ | 1866915882872078336 |
|---|---|
| author | Cho, Taewan Kim, Taeryang Choi, Andrew Jaeyong |
| author_facet | Cho, Taewan Kim, Taeryang Choi, Andrew Jaeyong |
| contents | Robotic and autonomous systems need dense spatial cues, but many monocular depth models are heavy, task-specific, or hard to attach to an existing multimodal stack. CLIP offers strong semantic representations, yet most CLIP-based depth methods still depend on text prompts or backbone updates, which complicate deployment in integrated control pipelines. We present SPACE-CLIP, a decoder-only depth framework that reads geometric cues directly from a frozen CLIP vision encoder and bypasses the text encoder at inference time. The model combines FiLM-conditioned semantic features from deep layers with structural features from shallow layers to recover both global scene layout and local geometric detail. Under the TFI-FB constraint (text-free inference and frozen vision backbone), SPACE-CLIP achieves AbsRel 0.0901 on KITTI and 0.1042 on NYU Depth V2, and the same dual-pathway decoder transfers to a frozen SigLIP backbone with comparable results. These findings show that a compact decoder can turn a shared foundation-model backbone into a reusable spatial perception module for embodied AI and autonomous robotic systems. Our model is available at https://github.com/taewan2002/space-clip |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_17657 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation Cho, Taewan Kim, Taeryang Choi, Andrew Jaeyong Computer Vision and Pattern Recognition Robotic and autonomous systems need dense spatial cues, but many monocular depth models are heavy, task-specific, or hard to attach to an existing multimodal stack. CLIP offers strong semantic representations, yet most CLIP-based depth methods still depend on text prompts or backbone updates, which complicate deployment in integrated control pipelines. We present SPACE-CLIP, a decoder-only depth framework that reads geometric cues directly from a frozen CLIP vision encoder and bypasses the text encoder at inference time. The model combines FiLM-conditioned semantic features from deep layers with structural features from shallow layers to recover both global scene layout and local geometric detail. Under the TFI-FB constraint (text-free inference and frozen vision backbone), SPACE-CLIP achieves AbsRel 0.0901 on KITTI and 0.1042 on NYU Depth V2, and the same dual-pathway decoder transfers to a frozen SigLIP backbone with comparable results. These findings show that a compact decoder can turn a shared foundation-model backbone into a reusable spatial perception module for embodied AI and autonomous robotic systems. Our model is available at https://github.com/taewan2002/space-clip |
| title | SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2601.17657 |