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.
Figures & tables
Fig. 1: Proposed shared-encoder integration of SPACE-CLIP. The depth module reuses a compatible vision encoder; downstream control is not evaluated.
Fig. 2: SPACE-CLIP depth decoder. Frozen CLIP features enter FiLM-conditioned semantic processing and a structural pathway, followed by staged fusion and depth prediction.
Fig. 3: NYU Depth V2 predictions. Columns show RGB input, reference depth, and SPACE-CLIP output.
Fig. 4: KITTI predictions. Columns show RGB input, reference depth, and SPACE-CLIP output.
Fig. 5: Learned pathway features: (a,b) cross-path CKA before and after fusion; (c,d) radial spectra and band energy. Lower CKA denotes lower representation similarity.
Fig. 6: Frequency removal from structural-pathway inputs. Large points show five-run means, small marks individual runs, and bars 95% scene-bootstrap intervals. Positive changes indicate increased AbsRel.