# MLSD Line Detection Canonical page: https://fuser.studio/models/mlsd-line-detection MLSD Line Detection in Fuser extracts straight structural lines from photos of rooms and buildings. Feed the map to ControlNet to keep perspective. ## Specs | Spec | Value | | --- | --- | | Inputs | Image | | Output | image | | Cost | 5 credits per run | Isolate clean architectural wireframes, perspective grids, and straight-line structural guides with single-shot precision Creator: NAVER / LINE Vision Also known as: M-LSD [Extract Line Skeletons](https://app.fuser.studio) ## How MLSD Line Detection works Transform photographic references and 3D renders into minimalist line-segment wireframes in three straightforward actions. ### Supply Reference Image Provide an architectural photo, interior design capture, or 3D render containing clear linear geometry. ### Tune Detection Thresholds Calibrate score and distance thresholds to balance fine wireframe fidelity against noise suppression. ### Export Wireframe Map Receive a high-contrast black-and-white structural line map ready to guide perspective-locked generation. ## What MLSD Line Detection is good at Extract pristine geometric scaffolding and perspective baselines to guide generative composition without transferring image noise. ### Perspective Grid Extraction Isolate precise perspective grids and building planes, stripping away distracting shadows and surface textures to produce clean white structural vectors on solid black. ### Score Confidence Control Tune the score threshold from 0.0 to 1.0 to eliminate faint texture noise or capture delicate structural lines across complex interior environments. ### Distance Segment Merging Adjust the distance threshold between 0.0 and 20.0 to resolve closely spaced window mullions and facade lattices without merging adjacent geometry. ### ControlNet Structural Guidance Generate ultra-lightweight structural scaffolding that locks camera perspective and room proportions into downstream ControlNet workflows. ## Made with MLSD Line Detection Explore how stark structural line maps anchor complex architectural perspectives, vehicle profiles, and editorial environments. ### High-fashion editorial perspective framing ### Constructivist album sleeve artwork ### Archival documentary urban perspective ### Minimalist interior gallery perspective ## What people build with MLSD Line Detection From architectural visualization to industrial product design, discover how creators enforce rigid geometric structure across workflows. ### Interior Architecture Transformation Extract crisp perspective grids and room dimensions from photo references to re-texture or re-furnish spaces while preserving exact wall placements. ### Industrial Hardware Design Maintain strict straight-line chassis contours and aerodynamic body planes when generating stylistic variations of vehicle and hardware designs. ### E-Commerce Product Staging Lock down the geometric boundaries of podiums, display stands, and shelving units to restyle commercial sets reliably. ### Fashion Set Construction Anchor models within stark architectural sets and runway structures to achieve rigorous editorial balance and perspective consistency. ### Cinematic Storyboard Scaffolding Capture vanishing points and architectural backdrops from location scouting photos to construct consistent cinematic storyboards. ## Frequently Asked Questions ### Is MLSD the same as M-LSD? Yes, MLSD stands for Mobile Line Segment Detection (M-LSD), developed by NAVER and LINE Vision. It is widely referenced as M-LSD in academic research and as the MLSD preprocessor in generative diffusion workflows. ### What imagery works best with MLSD line detection? MLSD is purpose-built for straight geometric geometry: interior room layouts, architectural building facades, street perspectives, furniture framing, and structural grids. It extracts crisp vector-like wireframes while stripping away surface textures, shadows, and color noise. ### When should I avoid using MLSD? Avoid using MLSD for organic silhouettes, human figures, animals, curved sculptures, vegetation, and soft drapery. Because the detector exclusively tracks straight segments, organic forms will either be ignored or rendered as fragmented visual artifacts. For organic shapes, reach for edge or depth preprocessors instead. ### How do Score Threshold and Distance Threshold work? Score Threshold sets the confidence cutoff between 0 and 1 (defaulting to 0.1) to eliminate noisy or faint line detections in busy textures. Distance Threshold spans from 0 to 20 (defaulting to 0.1) and controls line merging—lower values preserve fine parallel architectural details like window mullions, while higher values consolidate overlapping segments into simplified guides. ### Who created MLSD and how was it developed? NAVER and LINE Vision introduced M-LSD at AAAI 2022. The model uses a streamlined MobileNetV2 backbone with roughly 25,000 parameters and a tri-points formulation to deliver real-time single-shot line detection on resource-constrained hardware. ## Try MLSD Line Detection on Fuser Isolate clean architectural wireframes, perspective grids, and straight-line structural guides with single-shot precision [Extract Line Skeletons](https://app.fuser.studio) ## Related models - [Gemini Image](https://fuser.studio/models/gemini-image.md) - [GPT Image](https://fuser.studio/models/gpt-image.md) - [Seedream](https://fuser.studio/models/seedream.md) - [FLUX.3 Image](https://fuser.studio/models/flux-3-image.md) - [FLUX.2](https://fuser.studio/models/flux-2.md) - [ESRGAN Upscaler](https://fuser.studio/models/esrgan-upscaler.md) Node reference: [MLSD Line Detection docs](https://docs.fuser.studio/docs/nodes/image/mlsd-line-detection.md)