Results for “fastfoundationstereo”

Trains, evaluates, exports, and runs inference on FoundationStereo models for stereo depth estimation and 3D reconstruction from stereo image pairs.

Fine-tune Cosmos Reason video QA models using supervised fine-tuning with FSDP parallelism, including dataset preparation, spec construction, and AutoML support.

Create FastAPI routers with CRUD operations, authentication dependencies, and proper response models following established patterns.

Orchestrate token-heavy research, coding, and testing by delegating bounded tasks to cheaper subagents while reserving Claude Fable for architecture, synthesis, and final review.

Embeds target and source image parquets, then mines nearest-neighbour source images for augmentation in VCN AOI workflows.