{"id":"nvlabs-neuralangelo","name":"neuralangelo","homepage":"https://research.nvidia.com/labs/dir/neuralangelo/","repo_url":"https://github.com/NVlabs/neuralangelo","category":"ai-ml","subcategories":[],"tags":["ai-ml","computer-vision","3d-reconstruction","neural-rendering","neural-implicit","research-code"],"what_it_does":"Neuralangelo is an official implementation for high-fidelity neural surface reconstruction, built on the NVIDIA Imaginaire library. It provides training and inference (including isosurface/mesh extraction) for reconstructing a 3D surface from images/video with known camera poses.","use_cases":["Neural surface reconstruction from multi-view images or video frames with known camera poses","Research/prototyping of neural implicit surface methods (e.g., SDF-based reconstructions)","Generating textured or untextured meshes from trained checkpoints","Debugging camera pose / preprocessing pipelines for 3D reconstruction"],"not_for":["Production deployment as a network service (no REST/hosted API indicated)","Users who cannot run CUDA/PyTorch training workloads on GPUs","Environments requiring strict, enterprise-grade security/compliance controls typical of managed services"],"best_when":"You have a GPU environment (CUDA) and can follow the repo’s training/data-prep steps to run the pipeline end-to-end for research use.","avoid_when":"You need a lightweight, dependency-minimized library, or you need an external API/service with strong operational guarantees (auth, rate limits, SLA) rather than offline training scripts.","alternatives":["Instant-NGP (for neural radiance field/neural reconstruction approaches)","NeuS / other neural implicit surface reconstruction frameworks","COLMAP + classical reconstruction pipelines (where neural implicit refinement is unnecessary)"],"af_score":39.8,"security_score":41.8,"reliability_score":35.0,"package_type":"skill","discovery_source":["openclaw"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-29T14:59:50.091262+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":false,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":[],"oauth":false,"scopes":false,"notes":"No authentication mechanism for an API/service is described. Optional Weights & Biases (W&B) logging is supported, which typically requires W&B credentials if used."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information for the codebase is provided; it appears to be research software. Compute costs depend on GPU training/inference workloads."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":[],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":39.8,"security_score":41.8,"reliability_score":35.0,"mcp_server_quality":0.0,"documentation_accuracy":55.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":100.0,"rate_limit_clarity":0.0,"tls_enforcement":0.0,"auth_strength":100.0,"scope_granularity":0.0,"dependency_hygiene":45.0,"secret_handling":50.0,"security_notes":"This is offline research code, not a networked service. No API auth or TLS is applicable. The README mentions optional W&B logging but does not describe secret handling practices. Dependency hygiene/CVE status cannot be determined from the provided content.","uptime_documented":0.0,"version_stability":50.0,"breaking_changes_history":50.0,"error_recovery":40.0,"idempotency_support":"false","idempotency_notes":null,"pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["No programmatic API surface is provided; integration is via CLI scripts (train.py, extract_mesh.py) and config files.","Pipeline likely depends on substantial GPU memory (README mentions ~24GB for default configuration).","Reproducibility depends on external dependencies (Imaginaire) and correct dataset preprocessing/camera pose format.","Optional W&B logging introduces external service configuration if enabled."]}}