Problem
Research questions and friction points this paper is trying to address.
Deformable Linear Objects
Cable Tracing
State Estimation
Clutter
Occlusion
TRACE: Interactive Bi-Directional Tracing of Monochrome Cables Amid Clutter
🤖 AI Summary
This study addresses the challenge of state estimation for monochromatic cables in cluttered environments, where occlusions, overlaps, and crossings render traditional passive vision inadequate for effective tracking. To overcome this limitation, this work proposes an active perception framework that integrates bidirectional route tracing with interactive sensing. Specifically, two interaction primitives—Divergence Push and Cluster Dilation—are introduced to actively resolve visual ambiguities. By incorporating deformable linear object (DLO) modeling, the framework enables real-time parsing of multiple cables. This approach effectively overcomes tracking bottlenecks under severe occlusion, increasing the correctly tracked length ratio to approximately 90% in complex scenes. Furthermore, it achieves an average computation time of merely 0.4 seconds per cable, successfully unifying high accuracy with real-time performance.
📝 Abstract
Accurate state estimation (tracing) of Deformable Linear Objects (DLOs) such as cables is a critical challenge for data centers, manufacturing, construction, homes, and surgery, where precise cable management directly impacts operational safety and efficiency. However, resolving the state of multiple monochrome cables amid foreground and background clutter poses challenges due to occlusions, overlap, and ambiguous crossings. We present Two-way Routing And Cable Estimation (TRACE), which combines bi-directional cable tracing with interactive perception primitives-Divergence Push and Cluster Dilation-to actively resolve ambiguities. Evaluation with 110 physical experiments suggests that TRACE can increase the percentage of cable length correctly traced in complex scenarios (with up to 4 cables and 40 crossings) from ~60% with the strongest prior method, HANDLOOM 2.0, to ~90%, outperforming RT-DLO, Nano Banana Pro, and ChatGPT 5.2 as well. For a trial run on a workstation with an NVIDIA GeForce RTX 4090 GPU, the average computation time is 0.4 seconds per cable. Project website: https://trace-paper.github.io/.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Deformable Linear Objects
Bi-directional Tracing
Interactive Perception
Cable State Estimation
Ambiguity Resolution
🔎 Similar Papers
No similar papers found.
