Related papers: DEFOM-Stereo: Depth Foundation Model Based Stereo …
Our goal here is threefold: [1] To present a new dense-stereo matching algorithm, tMGM, that by combining the hierarchical logic of tSGM with the support structure of MGM achieves 6-8\% performance improvement over the baseline SGM (these…
Most existing algorithms for depth estimation from single monocular images need large quantities of metric groundtruth depths for supervised learning. We show that relative depth can be an informative cue for metric depth estimation and can…
Depth estimation is a fundamental task in computer vision with diverse applications. Recent advancements in deep learning have led to powerful depth foundation models (DFMs), yet their evaluation remains challenging due to inconsistencies…
Learning-based stereo matching has recently achieved promising results, yet still suffers difficulties in establishing reliable matches in weakly matchable regions that are textureless, non-Lambertian, or occluded. In this paper, we address…
While methods for monocular depth estimation have made significant strides on standard benchmarks, zero-shot metric depth estimation remains unsolved. Challenges include the joint modeling of indoor and outdoor scenes, which often exhibit…
Perceiving 3D objects from monocular inputs is crucial for robotic systems, given its economy compared to multi-sensor settings. It is notably difficult as a single image can not provide any clues for predicting absolute depth values.…
Obtaining accurate depth measurements out of a single image represents a fascinating solution to 3D sensing. CNNs led to considerable improvements in this field, and recent trends replaced the need for ground-truth labels with…
Monocular and stereo depth estimation offer complementary strengths: monocular methods capture rich contextual priors but lack geometric precision, while stereo approaches leverage epipolar geometry yet struggle with ambiguities such as…
Accurate stereo depth estimation plays a critical role in various 3D tasks in both indoor and outdoor environments. Recently, learning-based multi-view stereo methods have demonstrated competitive performance with a limited number of views.…
Stereo matching is an essential basis for various applications, but most stereo matching methods have poor generalization performance and require a fixed disparity search range. Moreover, current stereo matching methods focus on the scenes…
Stereo reconstruction models trained on small images do not generalize well to high-resolution data. Training a model on high-resolution image size faces difficulties of data availability and is often infeasible due to limited computing…
Current discriminative depth estimation methods often produce blurry artifacts, while generative approaches suffer from slow sampling due to curvatures in the noise-to-depth transport. Our method addresses these challenges by framing depth…
Monocular depth estimation has been extensively explored based on deep learning, yet its accuracy and generalization ability still lag far behind the stereo-based methods. To tackle this, a few recent studies have proposed to supervise the…
Monocular and binocular self-supervised depth estimations are two important and related tasks in computer vision, which aim to predict scene depths from single images and stereo image pairs respectively. In literature, the two tasks are…
Estimating depth from a monocular image is an ill-posed problem: when the camera projects a 3D scene onto a 2D plane, depth information is inherently and permanently lost. Nevertheless, recent work has shown impressive results in estimating…
Stereo matching is crucial for binocular stereo vision. Existing methods mainly focus on simple disparity map fusion to improve stereo matching, which require multiple dense or sparse disparity maps. In this paper, we propose a simple yet…
Computational stereo has reached a high level of accuracy, but degrades in the presence of occlusions, repeated textures, and correspondence errors along edges. We present a novel approach based on neural networks for depth estimation that…
Safe autonomous driving requires reliable 3D object detection-determining the 6 DoF pose and dimensions of objects of interest. Using stereo cameras to solve this task is a cost-effective alternative to the widely used LiDAR sensor. The…
We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches for accurate and robust tracking and mapping. Our core idea is to bridge flow…
Foundation-model-based monocular depth estimation offers a viable alternative to active sensors for robot perception, yet its computational cost often prohibits deployment on edge platforms. Existing methods perform independent per-frame…