Agents
SPACE-CLIP: Spatial Perception via Adaptive CLIP Embeddings for Monocular Depth Estimation
arXiv:2601.17657v4 Announce Type: replace Abstract: Robotic and autonomous systems need dense spatial cues, yet adding a dedicated depth estimator can duplicate visual processing already performed by
arXiv:2601.17657v4 Announce Type: replace Abstract: Robotic and autonomous systems need dense spatial cues, yet adding a dedicated depth estimator can duplicate visual processing already performed by a multimodal model. CLIP-based depth methods offer an alternative, but commonly rely on text-derived conditioning or backbone adaptation. We present SPACE-CLIP, a decoder-only framework for supervised monocular depth estimation with a frozen CLIP vision backbone and no text encoder at inference. A FiLM-conditioned semantic pathway combines global image context with multilevel patch features, while a structural pathway supplies separately processed spatial features to a hierarchical fusion decoder. Indoor and outdoor evaluations demonstrate depth reconstruction with this architecture, and controlled component comparisons support the contribution of the structural pathway. Layer-selection experiments and frequency interventions further characterize the structural pathway's contribution to depth reconstruction. A shared-backbone microbenchmark further illustrates the reduction in duplicated computation. SPACE-CLIP provides a modular approach to adding dense depth prediction to compatible visual perception stacks. Code is available at https://github.com/taewan2002/SPACE-CLIP.
Related
- DrivingDepth: Sparse-Prompted Pixel-wise Scale Correction for Driving Depth Estimation
- DAPM: UAV Monocular Depth Estimation from Any Height, Pitch, Roll and FOV
- Boosting Robustness for All-Weather Self-Supervised Depth Estimation in Autonomous Driving
- Speed in the Blind Spot: An Interpretability Analysis of Dynamic Perception in VLMs for Autonomous Driving
Source: arXiv cs.CV | 2026-10-06