Diffusion4RobustDepth: Images for Monocular Depth Estimation in Challenging Conditions

A dataset supporting the paper "Diffusion Models for Monocular Depth Estimation: Overcoming Challenging Conditions" (ECCV 2024). It is organized into three main categories: autonomous driving scenes with challenging images, a Transparent and Mirrored (ToM) objects dataset, and trained model weights. The dataset was uploaded by fabiotosi92 and last updated on September 28, 2024.

Use Cases

• Training depth estimation models based on the provided autonomous driving images with challenging conditions.
• Benchmarking model robustness using the dedicated Transparent and Mirrored (ToM) objects dataset.
• Fine-tuning pre-trained models using the included network weights.

Strengths

• Dataset is structured into three distinct, purpose-built categories: driving, ToM, and weights.
• Associated with a peer-reviewed publication (ECCV 2024), suggesting a research-grade purpose.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and total dataset size are unknown, which may limit suitability assessment.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

huggingface user fabiotosi92, associated with an ECCV 2024 paper.

Collection Method

Likely generated or compiled for the associated research.

Freshness

Last updated 2024-09-28 21:17:23.