Monocular Per-Object Distance Estimation with Masked Object Modeling
- URL: http://arxiv.org/abs/2401.03191v2
- Date: Tue, 04 Feb 2025 16:50:19 GMT
- Title: Monocular Per-Object Distance Estimation with Masked Object Modeling
- Authors: Aniello Panariello, Gianluca Mancusi, Fedy Haj Ali, Angelo Porrello, Simone Calderara, Rita Cucchiara,
- Abstract summary: Our paper draws inspiration from Masked Image Modeling (MiM) and extends it to multi-object tasks.
Our strategy, termed Masked Object Modeling (MoM), enables a novel application of masking techniques.
We evaluate the effectiveness of MoM on a novel reference architecture (DistFormer) on the standard KITTI, NuScenes, and MOT Synth datasets.
- Score: 33.59920084936913
- License:
- Abstract: Per-object distance estimation is critical in surveillance and autonomous driving, where safety is crucial. While existing methods rely on geometric or deep supervised features, only a few attempts have been made to leverage self-supervised learning. In this respect, our paper draws inspiration from Masked Image Modeling (MiM) and extends it to multi-object tasks. While MiM focuses on extracting global image-level representations, it struggles with individual objects within the image. This is detrimental for distance estimation, as objects far away correspond to negligible portions of the image. Conversely, our strategy, termed Masked Object Modeling (MoM), enables a novel application of masking techniques. In a few words, we devise an auxiliary objective that reconstructs the portions of the image pertaining to the objects detected in the scene. The training phase is performed in a single unified stage, simultaneously optimizing the masking objective and the downstream loss (i.e., distance estimation). We evaluate the effectiveness of MoM on a novel reference architecture (DistFormer) on the standard KITTI, NuScenes, and MOTSynth datasets. Our evaluation reveals that our framework surpasses the SoTA and highlights its robust regularization properties. The MoM strategy enhances both zero-shot and few-shot capabilities, from synthetic to real domain. Finally, it furthers the robustness of the model in the presence of occluded or poorly detected objects. Code is available at https://github.com/apanariello4/DistFormer
Related papers
- CVAM-Pose: Conditional Variational Autoencoder for Multi-Object Monocular Pose Estimation [3.5379836919221566]
Estimating rigid objects' poses is one of the fundamental problems in computer vision.
This paper presents a novel approach, CVAM-Pose, for multi-object monocular pose estimation.
arXiv Detail & Related papers (2024-10-11T17:26:27Z) - FoundationPose: Unified 6D Pose Estimation and Tracking of Novel Objects [55.77542145604758]
FoundationPose is a unified foundation model for 6D object pose estimation and tracking.
Our approach can be instantly applied at test-time to a novel object without fine-tuning.
arXiv Detail & Related papers (2023-12-13T18:28:09Z) - Self-Supervised Learning for Visual Relationship Detection through
Masked Bounding Box Reconstruction [6.798515070856465]
We present a novel self-supervised approach for representation learning, particularly for the task of Visual Relationship Detection (VRD)
Motivated by the effectiveness of Masked Image Modeling (MIM), we propose Masked Bounding Box Reconstruction (MBBR)
arXiv Detail & Related papers (2023-11-08T16:59:26Z) - UnsMOT: Unified Framework for Unsupervised Multi-Object Tracking with
Geometric Topology Guidance [6.577227592760559]
UnsMOT is a novel framework that combines appearance and motion features of objects with geometric information to provide more accurate tracking.
Experimental results show remarkable performance in terms of HOTA, IDF1, and MOTA metrics in comparison with state-of-the-art methods.
arXiv Detail & Related papers (2023-09-03T04:58:12Z) - Weakly-supervised Contrastive Learning for Unsupervised Object Discovery [52.696041556640516]
Unsupervised object discovery is promising due to its ability to discover objects in a generic manner.
We design a semantic-guided self-supervised learning model to extract high-level semantic features from images.
We introduce Principal Component Analysis (PCA) to localize object regions.
arXiv Detail & Related papers (2023-07-07T04:03:48Z) - MegaPose: 6D Pose Estimation of Novel Objects via Render & Compare [84.80956484848505]
MegaPose is a method to estimate the 6D pose of novel objects, that is, objects unseen during training.
We present a 6D pose refiner based on a render&compare strategy which can be applied to novel objects.
Second, we introduce a novel approach for coarse pose estimation which leverages a network trained to classify whether the pose error between a synthetic rendering and an observed image of the same object can be corrected by the refiner.
arXiv Detail & Related papers (2022-12-13T19:30:03Z) - DMODE: Differential Monocular Object Distance Estimation Module without Class Specific Information [8.552738832104101]
We propose DMODE, a class-agnostic method for monocular distance estimation.
DMODE estimates an object's distance by fusing its fluctuation in size over time with the camera's motion.
We evaluate our model on the KITTI MOTS dataset using ground-truth bounding box annotations and outputs from TrackRCNN and EagerMOT.
arXiv Detail & Related papers (2022-10-23T02:06:56Z) - Object-wise Masked Autoencoders for Fast Pre-training [13.757095663704858]
We show that current masked image encoding models learn the underlying relationship between all objects in the whole scene, instead of a single object representation.
We introduce a novel object selection and division strategy to drop non-object patches for learning object-wise representations by selective reconstruction with interested region masks.
Experiments on four commonly-used datasets demonstrate the effectiveness of our model in reducing the compute cost by 72% while achieving competitive performance.
arXiv Detail & Related papers (2022-05-28T05:13:45Z) - Discovering Objects that Can Move [55.743225595012966]
We study the problem of object discovery -- separating objects from the background without manual labels.
Existing approaches utilize appearance cues, such as color, texture, and location, to group pixels into object-like regions.
We choose to focus on dynamic objects -- entities that can move independently in the world.
arXiv Detail & Related papers (2022-03-18T21:13:56Z) - Synthesizing the Unseen for Zero-shot Object Detection [72.38031440014463]
We propose to synthesize visual features for unseen classes, so that the model learns both seen and unseen objects in the visual domain.
We use a novel generative model that uses class-semantics to not only generate the features but also to discriminatively separate them.
arXiv Detail & Related papers (2020-10-19T12:36:11Z) - Object-Centric Image Generation from Layouts [93.10217725729468]
We develop a layout-to-image-generation method to generate complex scenes with multiple objects.
Our method learns representations of the spatial relationships between objects in the scene, which lead to our model's improved layout-fidelity.
We introduce SceneFID, an object-centric adaptation of the popular Fr'echet Inception Distance metric, that is better suited for multi-object images.
arXiv Detail & Related papers (2020-03-16T21:40:09Z)
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.