Distilling Monocular Foundation Model for Fine-grained Depth Completion

• URL: http://arxiv.org/abs/2503.16970v1
• Date: Fri, 21 Mar 2025 09:34:01 GMT
• Title: Distilling Monocular Foundation Model for Fine-grained Depth Completion
• Authors: Yingping Liang, Yutao Hu, Wenqi Shao, Ying Fu,
• Abstract summary: We propose a two-stage knowledge distillation framework to provide dense supervision for depth completion.<n>In the first stage, we generate diverse training data from natural images, which distills geometric knowledge to depth completion.<n>In the second stage, we employ a scale- and shift-invariant loss to learn real-world scales when fine-tuning on real-world datasets.
• Score: 17.603217168518356
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Depth completion involves predicting dense depth maps from sparse LiDAR inputs. However, sparse depth annotations from sensors limit the availability of dense supervision, which is necessary for learning detailed geometric features. In this paper, we propose a two-stage knowledge distillation framework that leverages powerful monocular foundation models to provide dense supervision for depth completion. In the first stage, we introduce a pre-training strategy that generates diverse training data from natural images, which distills geometric knowledge to depth completion. Specifically, we simulate LiDAR scans by utilizing monocular depth and mesh reconstruction, thereby creating training data without requiring ground-truth depth. Besides, monocular depth estimation suffers from inherent scale ambiguity in real-world settings. To address this, in the second stage, we employ a scale- and shift-invariant loss (SSI Loss) to learn real-world scales when fine-tuning on real-world datasets. Our two-stage distillation framework enables depth completion models to harness the strengths of monocular foundation models. Experimental results demonstrate that models trained with our two-stage distillation framework achieve state-of-the-art performance, ranking \textbf{first place} on the KITTI benchmark. Code is available at https://github.com/Sharpiless/DMD3C

Related papers

• DepthLab: From Partial to Complete [80.58276388743306]
  Missing values remain a common challenge for depth data across its wide range of applications. This work bridges this gap with DepthLab, a foundation depth inpainting model powered by image diffusion priors. Our approach proves its worth in various downstream tasks, including 3D scene inpainting, text-to-3D scene generation, sparse-view reconstruction with DUST3R, and LiDAR depth completion.
  arXiv  Detail & Related papers  (2024-12-24T04:16:38Z)
• A Simple yet Effective Test-Time Adaptation for Zero-Shot Monocular Metric Depth Estimation [46.037640130193566]
  We propose a new method to rescale Depth Anything predictions using 3D points provided by sensors or techniques such as low-resolution LiDAR or structure-from-motion with poses given by an IMU. Our experiments highlight enhancements relative to zero-shot monocular metric depth estimation methods, competitive results compared to fine-tuned approaches and a better robustness than depth completion approaches.
  arXiv  Detail & Related papers  (2024-12-18T17:50:15Z)
• Prompting Depth Anything for 4K Resolution Accurate Metric Depth Estimation [108.04354143020886]
  We introduce prompting into depth foundation models, creating a new paradigm for metric depth estimation termed Prompt Depth Anything. We use a low-cost LiDAR as the prompt to guide the Depth Anything model for accurate metric depth output, achieving up to 4K resolution.
  arXiv  Detail & Related papers  (2024-12-18T16:32:12Z)
• MetricGold: Leveraging Text-To-Image Latent Diffusion Models for Metric Depth Estimation [9.639797094021988]
  MetricGold is a novel approach that harnesses generative diffusion model's rich priors to improve metric depth estimation.<n>Our experiments demonstrate robust generalization across diverse datasets, producing sharper and higher quality metric depth estimates.
  arXiv  Detail & Related papers  (2024-11-16T20:59:01Z)
• DepthSplat: Connecting Gaussian Splatting and Depth [90.06180236292866]
  We present DepthSplat to connect Gaussian splatting and depth estimation. We first contribute a robust multi-view depth model by leveraging pre-trained monocular depth features. We also show that Gaussian splatting can serve as an unsupervised pre-training objective.
  arXiv  Detail & Related papers  (2024-10-17T17:59:58Z)
• Robust Geometry-Preserving Depth Estimation Using Differentiable Rendering [93.94371335579321]
  We propose a learning framework that trains models to predict geometry-preserving depth without requiring extra data or annotations. Comprehensive experiments underscore our framework's superior generalization capabilities. Our innovative loss functions empower the model to autonomously recover domain-specific scale-and-shift coefficients.
  arXiv  Detail & Related papers  (2023-09-18T12:36:39Z)
• Towards Better Data Exploitation in Self-Supervised Monocular Depth Estimation [14.262669370264994]
  In this paper, we take two data augmentation techniques, namely Resizing-Cropping and Splitting-Permuting, to fully exploit the potential of training datasets. Specifically, the original image and the generated two augmented images are fed into the training pipeline simultaneously and we leverage them to conduct self-distillation. Experimental results demonstrate our method can achieve state-of-the-art performance on the KITTI benchmark, with both raw ground truth and improved ground truth.
  arXiv  Detail & Related papers  (2023-09-11T06:18:05Z)
• SC-DepthV3: Robust Self-supervised Monocular Depth Estimation for Dynamic Scenes [58.89295356901823]
  Self-supervised monocular depth estimation has shown impressive results in static scenes. It relies on the multi-view consistency assumption for training networks, however, that is violated in dynamic object regions. We introduce an external pretrained monocular depth estimation model for generating single-image depth prior. Our model can predict sharp and accurate depth maps, even when training from monocular videos of highly-dynamic scenes.
  arXiv  Detail & Related papers  (2022-11-07T16:17:47Z)
• Towards Accurate Reconstruction of 3D Scene Shape from A Single Monocular Image [91.71077190961688]
  We propose a two-stage framework that first predicts depth up to an unknown scale and shift from a single monocular image. We then exploits 3D point cloud data to predict the depth shift and the camera's focal length that allow us to recover 3D scene shapes. We test our depth model on nine unseen datasets and achieve state-of-the-art performance on zero-shot evaluation.
  arXiv  Detail & Related papers  (2022-08-28T16:20:14Z)
• Joint Prediction of Monocular Depth and Structure using Planar and Parallax Geometry [4.620624344434533]
  Supervised learning depth estimation methods can achieve good performance when trained on high-quality ground-truth, like LiDAR data. We propose a novel approach combining structure information from a promising Plane and Parallax geometry pipeline with depth information into a U-Net supervised learning network. Our model has impressive performance on depth prediction of thin objects and edges, and compared to structure prediction baseline, our model performs more robustly.
  arXiv  Detail & Related papers  (2022-07-13T17:04:05Z)
• Virtual Normal: Enforcing Geometric Constraints for Accurate and Robust Depth Prediction [87.08227378010874]
  We show the importance of the high-order 3D geometric constraints for depth prediction. By designing a loss term that enforces a simple geometric constraint, we significantly improve the accuracy and robustness of monocular depth estimation. We show state-of-the-art results of learning metric depth on NYU Depth-V2 and KITTI.
  arXiv  Detail & Related papers  (2021-03-07T00:08:21Z)

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.