DepthART: Scaling Foundation Monocular Depth to Tiny Models

• URL: http://arxiv.org/abs/2607.17099v1
• Date: Sun, 19 Jul 2026 06:54:52 GMT
• Title: DepthART: Scaling Foundation Monocular Depth to Tiny Models
• Abstract summary: DepthART is a compact MDE model for on-device deployment across diverse scenes.<n>We show how DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy.<n>We also provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an GTX A6000 at $2242/4482$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.
• Score: 51.10174763031444
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recent geometric foundation models (e.g., Metric3D, Depth Anything and UniDepth) have substantially improved monocular depth estimation (MDE) in both cross-scene generalization and metric-scale prediction, yet these gains have not translated to tiny models. We bridge this gap with DepthART (Depth Anything Rethought for Tiny Models), which is a compact MDE model for on-device deployment across diverse scenes. We first identify two capacity-driven bottlenecks in tiny models: (i) overfitting to dataset-specific distribution bias and (ii) unstable metric adaptation under camera shift, where full fine-tuning easily damages transferable geometry. Accordingly, DepthART combines two simple but effective strategies: a bias-resistant data sampling scheme to reduce distribution bias under the same training budget, and a camera-conditioned fine-tuning protocol that freezes the distilled encoder and adjusts metric scale conditioned on intrinsics while better preserving cross-dataset generalization. Across datasets, DepthART consistently surpasses previous tiny baselines in both zero-shot generalization and metric accuracy (e.g., zero-shot $δ_1$=0.964 for DepthART-S on NYUD v2), and in some cases approaches heavy models. We further provide a scalable model family, with DepthART-S reaching 347/245 FPS (strict FP32) on an RTX A6000 at $224^2/448^2$, 102 FPS (TF32) on a Orin NX 8GB, and over 15 FPS (FP32) on a Jetson Nano 4GB.

Related papers

• GeoRay: Gauge-Aware Feed-Forward Satellite 3D Reconstruction in the Geodetic Frame [11.043507429399414]
  Method treats perspective-pretrained features, absolute elevation, and monocular and multi-view cues.<n> lightweight ray-consistent adapters make a frozen backbone matchable along native RPC rays.<n>bench, our absolute-frame benchmark of eighteen systems, scores absolute placement without registration or test-reference leakage.
  arXiv  Detail & Related papers  (2026-08-30T09:27:36Z)
• LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels [49.35636088613484]
  Joint Embedding Predictive Architectures (JEPAs) offer a compelling framework for learning world models in compact latent spaces.<n>We introduce LeModelWorld, the first JEPA that trains stably end-to-end from raw pixels using only two loss terms.<n>With 15M parameters trainable on a single GPU in a few hours, LeWM plans up to 48x faster than foundation-model-based world models.
  arXiv  Detail & Related papers  (2026-03-13T19:48:14Z)
• From Editor to Dense Geometry Estimator [77.21804448599009]
  We introduce textbfFE2E, a framework that adapts an advanced editing model based on Diffusion Transformer (DiT) architecture for dense geometry prediction.<n>FE2E achieves over 35% performance gains on the ETH3D dataset and outperforms the DepthAnything series, which is trained on 100$times$ data.
  arXiv  Detail & Related papers  (2025-09-04T15:58:50Z)
• UniDepthV2: Universal Monocular Metric Depth Estimation Made Simpler [62.06785782635153]
  We propose a new model, UniDepthV2, capable of reconstructing metric 3D scenes from solely single images across domains.<n>UniDepthV2 directly predicts metric 3D points from the input image at inference time without any additional information.<n>Our model exploits a pseudo-spherical output representation, which disentangles the camera and depth representations.
  arXiv  Detail & Related papers  (2025-02-27T14:03:15Z)
• Enhanced Encoder-Decoder Architecture for Accurate Monocular Depth Estimation [0.0]
  This paper introduces a novel deep learning-based approach using an enhanced encoder-decoder architecture.<n>It incorporates multi-scale feature extraction to enhance depth prediction accuracy across various object sizes and distances.<n> Experimental results on the KITTI dataset show that our model achieves a significantly faster inference time of 0.019 seconds.
  arXiv  Detail & Related papers  (2024-10-15T13:46:19Z)
• Metric3Dv2: A Versatile Monocular Geometric Foundation Model for Zero-shot Metric Depth and Surface Normal Estimation [74.28509379811084]
  Metric3D v2 is a geometric foundation model for zero-shot metric depth and surface normal estimation from a single image.<n>We propose solutions for both metric depth estimation and surface normal estimation.<n>Our method enables the accurate recovery of metric 3D structures on randomly collected internet images.
  arXiv  Detail & Related papers  (2024-03-22T02:30:46Z)
• Metric3D: Towards Zero-shot Metric 3D Prediction from A Single Image [85.91935485902708]
  We show that the key to a zero-shot single-view metric depth model lies in the combination of large-scale data training and resolving the metric ambiguity from various camera models. We propose a canonical camera space transformation module, which explicitly addresses the ambiguity problems and can be effortlessly plugged into existing monocular models. Our method enables the accurate recovery of metric 3D structures on randomly collected internet images.
  arXiv  Detail & Related papers  (2023-07-20T16:14:23Z)
• Unsupervised Learning of Depth, Camera Pose and Optical Flow from Monocular Video [3.838877984537827]
  DFPNet -- an unsupervised, joint learning system for monocular Depth, Optical Flow and egomotion estimation. We leverage this fact to jointly train all the three components in an end-to-end manner. We are able to reduce the model size to less than 5% (8.4M parameters) of state-of-the-art DFP models.
  arXiv  Detail & Related papers  (2022-05-19T19:47:41Z)

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.