Weather-Conditioned Depth Anything

• URL: http://arxiv.org/abs/2609.04827v1
• Date: Fri, 04 Sep 2026 07:29:49 GMT
• Title: Weather-Conditioned Depth Anything
• Abstract summary: We present Weather-Conditioned Depth Anything (DA-W), a framework that explicitly disentangles style from content for weather-robust depth estimation.<n>Specifically, we introduce a Style Filter trained on a curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings.<n>Such a lightweight modulation allows a single unified model to robustly adapt to diverse conditions, including fog, rain, snow, and low-light.
• Score: 21.76633155195026
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, they still suffer from critical failures under adverse weather conditions, such as fog, rain, snow, or at night. To address this, we present Weather-Conditioned Depth Anything (DA-W), a framework that explicitly disentangles style from content for weather-robust depth estimation. Specifically, we introduce a Style Filter trained on a curated mix of real and synthetic degradation datasets to extract content-independent, degradation-aware weather embeddings. This style embedding is then injected into the Depth Anything backbone using a parameter-efficient, zero-initialized adapter. Such a lightweight modulation allows a single unified model to robustly adapt to diverse conditions, including fog, rain, snow, and low-light, while avoiding catastrophic forgetting of its core generalization abilities in normal conditions. We train the adapter using a pseudo-label distillation and alignment strategy. Our comprehensive experiments demonstrate that our proposed DA-W achieves state-of-the-art robust depth estimation, improving AbsRel by an average of 3.7% on our curated weather benchmarks, while matching or slightly outperforming performance on standard clean benchmarks. Our project page is available at https://zhaoming-tamu.github.io/WCDA/.

Related papers

• NimbusGS: Unified 3D Scene Reconstruction under Hybrid Weather [83.14198482357388]
  We present NimbusGS, a unified framework for reconstructing high-quality 3D scenes from degraded multi-view inputs.<n>Unlike existing methods that target specific weather types, NimbusGS addresses the broader challenge of generalization.
  arXiv  Detail & Related papers  (2026-03-28T10:46:29Z)
• Depth Completion as Parameter-Efficient Test-Time Adaptation [66.72360181325877]
  CAPA is a parameter-efficient test-time optimization framework that adapts pre-trained 3D foundation models (FMs) for depth completion.<n>For videos, CAPA introduces sequence-level parameter sharing, jointly adapting all frames to exploit temporal correlations, improve robustness, and enforce multi-frame consistency.
  arXiv  Detail & Related papers  (2026-02-16T13:53:23Z)
• Depth Anything at Any Condition [21.800621254831718]
  We present Depth Anything at Any Condition (DepthAnything-AC), a foundation monocular depth estimation (MDE) model capable of handling diverse environmental conditions.<n>Previous foundation MDE models achieve impressive performance across general scenes but not perform well in complex open-world environments.<n>We propose an unsupervised consistency regularization finetuning paradigm that requires only a relatively small amount of unlabeled data.
  arXiv  Detail & Related papers  (2025-07-02T12:05:57Z)
• Always Clear Depth: Robust Monocular Depth Estimation under Adverse Weather [48.65180004211851]
  We present a robust monocular depth estimation method called textbfACDepth from the perspective of high-quality training data generation and domain adaptation.<n>Specifically, we introduce a one-step diffusion model for generating samples that simulate adverse weather conditions, constructing a multi-tuple degradation dataset during training.<n>We elaborate on a multi-granularity knowledge distillation strategy (MKD) that encourages the student network to absorb knowledge from both the teacher model and pretrained Depth Anything V2.
  arXiv  Detail & Related papers  (2025-05-18T02:30:47Z)
• HazyDet: Open-Source Benchmark for Drone-View Object Detection with Depth-Cues in Hazy Scenes [54.24350833692194]
  HazyDet is the first, large-scale benchmark specifically designed for drone-view object detection in hazy conditions.<n>We propose the Depth-Conditioned Detector (DeCoDet) to address the severe visual degradation induced by haze.<n>HazyDet provides a challenging and realistic testbed for advancing detection algorithms.
  arXiv  Detail & Related papers  (2024-09-30T00:11:40Z)
• Dusk Till Dawn: Self-supervised Nighttime Stereo Depth Estimation using Visual Foundation Models [16.792458193160407]
  Self-supervised depth estimation algorithms rely heavily on frame-warping relationships. We introduce an algorithm designed to achieve accurate self-supervised stereo depth estimation focusing on nighttime conditions.
  arXiv  Detail & Related papers  (2024-05-18T03:07:23Z)
• Into the Fog: Evaluating Robustness of Multiple Object Tracking [11.271890273740143]
  State-of-the-art Multiple Object Tracking (MOT) approaches have shown remarkable performance when trained and evaluated on current benchmarks. These benchmarks primarily consist of clear weather scenarios, overlooking adverse atmospheric conditions such as fog, haze, smoke and dust. We introduce physics-based volumetric fog simulation method for arbitrary MOT datasets, utilizing frame-by-frame monocular depth estimation and a fog formation optical model.
  arXiv  Detail & Related papers  (2024-04-12T21:41:50Z)
• WeatherDepth: Curriculum Contrastive Learning for Self-Supervised Depth Estimation under Adverse Weather Conditions [42.99525455786019]
  We propose WeatherDepth, a self-supervised robust depth estimation model with curriculum contrastive learning. The proposed solution is proven to be easily incorporated into various architectures and demonstrates state-of-the-art (SoTA) performance on both synthetic and real weather datasets.
  arXiv  Detail & Related papers  (2023-10-09T09:26:27Z)
• Robust Monocular Depth Estimation under Challenging Conditions [81.57697198031975]
  State-of-the-art monocular depth estimation approaches are highly unreliable under challenging illumination and weather conditions. We tackle these safety-critical issues with md4all: a simple and effective solution that works reliably under both adverse and ideal conditions.
  arXiv  Detail & Related papers  (2023-08-18T17:59:01Z)
• Self-supervised Monocular Depth Estimation: Let's Talk About The Weather [2.836066255205732]
  Current, self-supervised depth estimation architectures rely on clear and sunny weather scenes to train deep neural networks. In this paper, we put forward a method that uses augmentations to remedy this problem. We present extensive testing to show that our method, Robust-Depth, achieves SotA performance on the KITTI dataset.
  arXiv  Detail & Related papers  (2023-07-17T09:50:03Z)
• DARF: Depth-Aware Generalizable Neural Radiance Field [51.29437249009986]
  We propose the Depth-Aware Generalizable Neural Radiance Field (DARF) with a Depth-Aware Dynamic Sampling (DADS) strategy.<n>Our framework infers the unseen scenes on both pixel level and geometry level with only a few input images.<n>Compared with state-of-the-art generalizable NeRF methods, DARF reduces samples by 50%, while improving rendering quality and depth estimation.
  arXiv  Detail & Related papers  (2022-12-05T14:00:59Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.