Tackling 3D ToF Artifacts Through Learning and the FLAT Dataset

2018/07/26 by Qi Guo, Guo, Qi, Iuri Frosio +7 · 2 citations
Computer Science · Physics and Astronomy · #Advanced Optical Sensing Technologies #Advanced Vision and Imaging #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Optical measurement and interference techniques

paper · pdf · doi:10.48550/arxiv.1807.10376

openalex publication_date 2018/07/26 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Scene motion, multiple reflections, and sensor noise introduce artifacts in the depth reconstruction performed by time-of-flight cameras. We propose a two-stage, deep-learning approach to address all of these sources of artifacts simultaneously. We also introduce FLAT, a synthetic dataset of 2000 ToF measurements that capture all of these nonidealities, and allows to simulate different camera hardware. Using the Kinect 2 camera as a baseline, we show improved reconstruction errors over state-of-the-art methods, on both simulated and real data.

Cited by

• Learnable Fractional Reaction-Diffusion Dynamics for Under-Display ToF Imaging and Beyond
• Consistent Time-of-Flight Depth Denoising via Graph-Informed Geometric Attention

Related

• Learning the Correction for Multi-Path Deviations in Time-of-Flight Cameras
• RADU: Ray-Aligned Depth Update Convolutions for ToF Data Denoising
• Compressive Time-of-Flight 3D Imaging Using Block-Structured Sensing Matrices
• TöRF: Time-of-Flight Radiance Fields for Dynamic Scene View Synthesis
• Color-Guided Flying Pixel Correction in Depth Images