DGPINet-KD: Deep Guided and Progressive Integration Network with Knowledge Distillation for RGB-D Indoor Scene Analysis
Significant advancements in RGB-D semantic segmentation have been made owing to the
increasing availability of robust depth information. Most researchers have combined depth …
increasing availability of robust depth information. Most researchers have combined depth …
Meta-optimization for higher model generalizability in single-image depth prediction
Model generalizability to unseen datasets, concerned with in-the-wild robustness, is less
studied for indoor single-image depth prediction. We leverage gradient-based meta-learning …
studied for indoor single-image depth prediction. We leverage gradient-based meta-learning …
GeoBench: Benchmarking and Analyzing Monocular Geometry Estimation Models
Recent advances in discriminative and generative pretraining have yielded geometry
estimation models with strong generalization capabilities. While discriminative monocular …
estimation models with strong generalization capabilities. While discriminative monocular …
Scene completeness-aware lidar depth completion for driving scenario
This paper introduces Scene Completeness-Aware Depth Completion (SCADC) to complete
raw lidar scans into dense depth maps with fine and complete scene structures. Recent …
raw lidar scans into dense depth maps with fine and complete scene structures. Recent …