Depth estimation is an essential task toward full scene understanding since it allows the projection of rich semantic information captured by cameras into 3D space. While the field has gained much attention recently, datasets for depth estimation lack scene diversity or sensor modalities. This work presents the ADUULM-360 dataset, a novel multi-modal dataset for depth estimation. The ADUULM-360 dataset covers all established autonomous driving sensor modalities, cameras, lidars, and radars. It covers a frontal-facing stereo setup, six surround cameras covering the full 360-degree, two high-resolution long-range lidar sensors, and five long-range radar sensors. It is also the first depth estimation dataset that contains diverse scenes in good and adverse weather conditions. We conduct extensive experiments using state-of-the-art self-supervised depth estimation methods under different training tasks, such as monocular training, stereo training, and full surround training. Discussing these results, we demonstrate common limitations of state-of-the-art methods, especially in adverse weather conditions, which hopefully will inspire future research in this area. Our dataset, development kit, and trained baselines are available at https://github.com/uulm-mrm/aduulm_360_dataset.
Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject optimization which does not meet the requirement of real-time rendering in an interactive application. We propose a generalizable Gaussian Splatting approach for high-resolution image rendering under a sparse-view camera setting. To this end, we introduce Gaussian parameter maps defined on the source views and directly regress Gaussian properties for instant novel view synthesis without any fine-tuning or optimization. We train our Gaussian parameter regression module on human-only data or human-scene data, jointly with a depth estimation module to lift 2D parameter maps to 3D space. The proposed framework is fully differentiable with both depth and rendering supervision or with only rendering supervision. We further introduce a regularization term and an epipolar attention mechanism to preserve geometry consistency between two source views, especially when neglecting depth supervision. Experiments on several datasets demonstrate that our method outperforms state-of-the-art methods while achieving an exceeding rendering speed.
This paper shows that the autoregressive model is an effective and scalable monocular depth estimator. Our idea is simple: We tackle the monocular depth estimation (MDE) task with an autoregressive prediction paradigm, based on two core designs. First, our depth autoregressive model (DAR) treats the depth map of different resolutions as a set of tokens, and conducts the low-to-high resolution autoregressive objective with a patch-wise casual mask. Second, our DAR recursively discretizes the entire depth range into more compact intervals, and attains the coarse-to-fine granularity autoregressive objective in an ordinal-regression manner. By coupling these two autoregressive objectives, our DAR establishes new state-of-the-art (SOTA) on KITTI and NYU Depth v2 by clear margins. Further, our scalable approach allows us to scale the model up to 2.0B and achieve the best RMSE of 1.799 on the KITTI dataset (5% improvement) compared to 1.896 by the current SOTA (Depth Anything). DAR further showcases zero-shot generalization ability on unseen datasets. These results suggest that DAR yields superior performance with an autoregressive prediction paradigm, providing a promising approach to equip modern autoregressive large models (e.g., GPT-4o) with depth estimation capabilities.
Recovering metric depth from a single image remains a fundamental challenge in computer vision, requiring both scene understanding and accurate scaling. While deep learning has advanced monocular depth estimation, current models often struggle with unfamiliar scenes and layouts, particularly in zero-shot scenarios and when predicting scale-ergodic metric depth. We present MetricGold, a novel approach that harnesses generative diffusion model's rich priors to improve metric depth estimation. Building upon recent advances in MariGold, DDVM and Depth Anything V2 respectively, our method combines latent diffusion, log-scaled metric depth representation, and synthetic data training. MetricGold achieves efficient training on a single RTX 3090 within two days using photo-realistic synthetic data from HyperSIM, VirtualKitti, and TartanAir. Our experiments demonstrate robust generalization across diverse datasets, producing sharper and higher quality metric depth estimates compared to existing approaches.
Creating large-scale interactive 3D environments is essential for the development of Robotics and Embodied AI research. Current methods, including manual design, procedural generation, diffusion-based scene generation, and large language model (LLM) guided scene design, are hindered by limitations such as excessive human effort, reliance on predefined rules or training datasets, and limited 3D spatial reasoning ability. Since pre-trained 2D image generative models better capture scene and object configuration than LLMs, we address these challenges by introducing Architect, a generative framework that creates complex and realistic 3D embodied environments leveraging diffusion-based 2D image inpainting. In detail, we utilize foundation visual perception models to obtain each generated object from the image and leverage pre-trained depth estimation models to lift the generated 2D image to 3D space. Our pipeline is further extended to a hierarchical and iterative inpainting process to continuously generate placement of large furniture and small objects to enrich the scene. This iterative structure brings the flexibility for our method to generate or refine scenes from various starting points, such as text, floor plans, or pre-arranged environments.
Differentiable rendering techniques like Gaussian Splatting and Neural Radiance Fields have become powerful tools for generating high-fidelity models of 3D objects and scenes. Their ability to produce both physically plausible and differentiable models of scenes are key ingredient needed to produce physically plausible adversarial attacks on DNNs. However, the adversarial machine learning community has yet to fully explore these capabilities, partly due to differing attack goals (e.g., misclassification, misdetection) and a wide range of possible scene manipulations used to achieve them (e.g., alter texture, mesh). This survey contributes the first framework that unifies diverse goals and tasks, facilitating easy comparison of existing work, identifying research gaps, and highlighting future directions - ranging from expanding attack goals and tasks to account for new modalities, state-of-the-art models, tools, and pipelines, to underscoring the importance of studying real-world threats in complex scenes.
Stereo depth estimation is a fundamental component in augmented reality (AR) applications. Although AR applications require very low latency for their real-time applications, traditional depth estimation models often rely on time-consuming preprocessing steps such as rectification to achieve high accuracy. Also, non standard ML operator based algorithms such as cost volume also require significant latency, which is aggravated on compute resource-constrained mobile platforms. Therefore, we develop hardware-friendly alternatives to the costly cost volume and preprocessing and design two new models based on them, MultiHeadDepth and HomoDepth. Our approaches for cost volume is replacing it with a new group-pointwise convolution-based operator and approximation of consine similarity based on layernorm and dot product. For online stereo rectification (preprocessing), we introduce homograhy matrix prediction network with a rectification positional encoding (RPE), which delivers both low latency and robustness to unrectified images, which eliminates the needs for preprocessing. Our MultiHeadDepth, which includes optimized cost volume, provides 11.8-30.3% improvements in accuracy and 22.9-25.2% reduction in latency compared to a state-of-the-art depth estimation model for AR glasses from industry. Our HomoDepth, which includes optimized preprocessing (Homograhpy + RPE) upon MultiHeadDepth, can process unrectified images and reduce the end-to-end latency by 44.5%. We adopt a multi-task learning framework to handle misaligned stereo inputs on HomoDepth, which reduces theAbsRel error by 10.0-24.3%. The results demonstrate the efficacy of our approaches in achieving both high model performance with low latency, which makes a step forward toward practical depth estimation on future AR devices.
The generalization and performance of stereo matching networks are limited due to the domain gap of the existing synthetic datasets and the sparseness of GT labels in the real datasets. In contrast, monocular depth estimation has achieved significant advancements, benefiting from large-scale depth datasets and self-supervised strategies. To bridge the performance gap between monocular depth estimation and stereo matching, we propose leveraging monocular knowledge transfer to enhance stereo matching, namely Mono2Stereo. We introduce knowledge transfer with a two-stage training process, comprising synthetic data pre-training and real-world data fine-tuning. In the pre-training stage, we design a data generation pipeline that synthesizes stereo training data from monocular images. This pipeline utilizes monocular depth for warping and novel view synthesis and employs our proposed Edge-Aware (EA) inpainting module to fill in missing contents in the generated images. In the fine-tuning stage, we introduce a Sparse-to-Dense Knowledge Distillation (S2DKD) strategy encouraging the distributions of predictions to align with dense monocular depths. This strategy mitigates issues with edge blurring in sparse real-world labels and enhances overall consistency. Experimental results demonstrate that our pre-trained model exhibits strong zero-shot generalization capabilities. Furthermore, domain-specific fine-tuning using our pre-trained model and S2DKD strategy significantly increments in-domain performance. The code will be made available soon.
OpenStreetMap (OSM), a rich and versatile source of volunteered geographic information (VGI), facilitates human self-localization and scene understanding by integrating nearby visual observations with vectorized map data. However, the disparity in modalities and perspectives poses a major challenge for effectively matching camera imagery with compact map representations, thereby limiting the full potential of VGI data in real-world localization applications. Inspired by the fact that the human brain relies on the fusion of geometric and semantic understanding for spatial localization tasks, we propose the OSMLoc in this paper. OSMLoc is a brain-inspired visual localization approach based on first-person-view images against the OSM maps. It integrates semantic and geometric guidance to significantly improve accuracy, robustness, and generalization capability. First, we equip the OSMLoc with the visual foundational model to extract powerful image features. Second, a geometry-guided depth distribution adapter is proposed to bridge the monocular depth estimation and camera-to-BEV transform. Thirdly, the semantic embeddings from the OSM data are utilized as auxiliary guidance for image-to-OSM feature matching. To validate the proposed OSMLoc, we collect a worldwide cross-area and cross-condition (CC) benchmark for extensive evaluation. Experiments on the MGL dataset, CC validation benchmark, and KITTI dataset have demonstrated the superiority of our method. Code, pre-trained models, CC validation benchmark, and additional results are available at: https://github.com/WHU-USI3DV/OSMLoc.
Incorporating inductive bias by embedding geometric entities (such as rays) as input has proven successful in multi-view learning. However, the methods adopting this technique typically lack equivariance, which is crucial for effective 3D learning. Equivariance serves as a valuable inductive prior, aiding in the generation of robust multi-view features for 3D scene understanding. In this paper, we explore the application of equivariant multi-view learning to depth estimation, not only recognizing its significance for computer vision and robotics but also addressing the limitations of previous research. Most prior studies have either overlooked equivariance in this setting or achieved only approximate equivariance through data augmentation, which often leads to inconsistencies across different reference frames. To address this issue, we propose to embed $SE(3)$ equivariance into the Perceiver IO architecture. We employ Spherical Harmonics for positional encoding to ensure 3D rotation equivariance, and develop a specialized equivariant encoder and decoder within the Perceiver IO architecture. To validate our model, we applied it to the task of stereo depth estimation, achieving state of the art results on real-world datasets without explicit geometric constraints or extensive data augmentation.
In this paper, we argue that iterative computation with diffusion models offers a powerful paradigm for not only generation but also visual perception tasks. We unify tasks such as depth estimation, optical flow, and amodal segmentation under the framework of image-to-image translation, and show how diffusion models benefit from scaling training and test-time compute for these perceptual tasks. Through a careful analysis of these scaling properties, we formulate compute-optimal training and inference recipes to scale diffusion models for visual perception tasks. Our models achieve competitive performance to state-of-the-art methods using significantly less data and compute. To access our code and models, see https://scaling-diffusion-perception.github.io .
More and more research works fuse the LiDAR and camera information to improve the 3D object detection of the autonomous driving system. Recently, a simple yet effective fusion framework has achieved an excellent detection performance, fusing the LiDAR and camera features in a unified bird's-eye-view (BEV) space. In this paper, we propose a LiDAR-camera fusion framework, named SimpleBEV, for accurate 3D object detection, which follows the BEV-based fusion framework and improves the camera and LiDAR encoders, respectively. Specifically, we perform the camera-based depth estimation using a cascade network and rectify the depth results with the depth information derived from the LiDAR points. Meanwhile, an auxiliary branch that implements the 3D object detection using only the camera-BEV features is introduced to exploit the camera information during the training phase. Besides, we improve the LiDAR feature extractor by fusing the multi-scaled sparse convolutional features. Experimental results demonstrate the effectiveness of our proposed method. Our method achieves 77.6\% NDS accuracy on the nuScenes dataset, showcasing superior performance in the 3D object detection track.
In this paper, we propose a novel method for monocular depth estimation in dynamic scenes. We first explore the arbitrariness of object's movement trajectory in dynamic scenes theoretically. To overcome the arbitrariness, we use assume that points move along a straight line over short distances and then summarize it as a triangular constraint loss in two dimensional Euclidean space. To overcome the depth inconsistency problem around the edges, we propose a deformable support window module that learns features from different shapes of objects, making depth value more accurate around edge area. The proposed model is trained and tested on two outdoor datasets - KITTI and Make3D, as well as an indoor dataset - NYU Depth V2. The quantitative and qualitative results reported on these datasets demonstrate the success of our proposed model when compared against other approaches. Ablation study results on the KITTI dataset also validate the effectiveness of the proposed pixel movement prediction module as well as the deformable support window module.
In this study, we propose a high-performance disparity (depth) estimation method using dual-pixel (DP) images with few parameters. Conventional end-to-end deep-learning methods have many parameters but do not fully exploit disparity constraints, which limits their performance. Therefore, we propose a lightweight disparity estimation method based on a completion-based network that explicitly constrains disparity and learns the physical and systemic disparity properties of DP. By modeling the DP-specific disparity error parametrically and using it for sampling during training, the network acquires the unique properties of DP and enhances robustness. This learning also allows us to use a common RGB-D dataset for training without a DP dataset, which is labor-intensive to acquire. Furthermore, we propose a non-learning-based refinement framework that efficiently handles inherent disparity expansion errors by appropriately refining the confidence map of the network output. As a result, the proposed method achieved state-of-the-art results while reducing the overall system size to 1/5 of that of the conventional method, even without using the DP dataset for training, thereby demonstrating its effectiveness. The code and dataset are available on our project site.
Monocular depth estimation has shown promise in general imaging tasks, aiding in localization and 3D reconstruction. While effective in various domains, its application to bronchoscopic images is hindered by the lack of labeled data, challenging the use of supervised learning methods. In this work, we propose a transfer learning framework that leverages synthetic data with depth labels for training and adapts domain knowledge for accurate depth estimation in real bronchoscope data. Our network demonstrates improved depth prediction on real footage using domain adaptation compared to training solely on synthetic data, validating our approach.
Depth estimation is a crucial technology in robotics. Recently, self-supervised depth estimation methods have demonstrated great potential as they can efficiently leverage large amounts of unlabelled real-world data. However, most existing methods are designed under the assumption of static scenes, which hinders their adaptability in dynamic environments. To address this issue, we present D$^3$epth, a novel method for self-supervised depth estimation in dynamic scenes. It tackles the challenge of dynamic objects from two key perspectives. First, within the self-supervised framework, we design a reprojection constraint to identify regions likely to contain dynamic objects, allowing the construction of a dynamic mask that mitigates their impact at the loss level. Second, for multi-frame depth estimation, we introduce a cost volume auto-masking strategy that leverages adjacent frames to identify regions associated with dynamic objects and generate corresponding masks. This provides guidance for subsequent processes. Furthermore, we propose a spectral entropy uncertainty module that incorporates spectral entropy to guide uncertainty estimation during depth fusion, effectively addressing issues arising from cost volume computation in dynamic environments. Extensive experiments on KITTI and Cityscapes datasets demonstrate that the proposed method consistently outperforms existing self-supervised monocular depth estimation baselines. Code is available at \url{https://github.com/Csyunling/D3epth}.
Depth estimation under adverse conditions remains a significant challenge. Recently, multi-spectral depth estimation, which integrates both visible light and thermal images, has shown promise in addressing this issue. However, existing algorithms struggle with precise pixel-level feature matching, limiting their ability to fully exploit geometric constraints across different spectra. To address this, we propose a novel framework incorporating stereo depth estimation to enforce accurate geometric constraints. In particular, we treat the visible light and thermal images as a stereo pair and utilize a Cross-modal Feature Matching (CFM) Module to construct a cost volume for pixel-level matching. To mitigate the effects of poor lighting on stereo matching, we introduce Degradation Masking, which leverages robust monocular thermal depth estimation in degraded regions. Our method achieves state-of-the-art (SOTA) performance on the Multi-Spectral Stereo (MS2) dataset, with qualitative evaluations demonstrating high-quality depth maps under varying lighting conditions.
As object detection techniques continue to evolve, understanding their relationships with complementary visual tasks becomes crucial for optimising model architectures and computational resources. This paper investigates the correlations between object detection accuracy and two fundamental visual tasks: depth prediction and visual saliency prediction. Through comprehensive experiments using state-of-the-art models (DeepGaze IIE, Depth Anything, DPT-Large, and Itti's model) on COCO and Pascal VOC datasets, we find that visual saliency shows consistently stronger correlations with object detection accuracy (mA$\rho$ up to 0.459 on Pascal VOC) compared to depth prediction (mA$\rho$ up to 0.283). Our analysis reveals significant variations in these correlations across object categories, with larger objects showing correlation values up to three times higher than smaller objects. These findings suggest incorporating visual saliency features into object detection architectures could be more beneficial than depth information, particularly for specific object categories. The observed category-specific variations also provide insights for targeted feature engineering and dataset design improvements, potentially leading to more efficient and accurate object detection systems.
Monocular Depth Estimation (MDE) is a pivotal component of vision-based Autonomous Driving (AD) systems, enabling vehicles to estimate the depth of surrounding objects using a single camera image. This estimation guides essential driving decisions, such as braking before an obstacle or changing lanes to avoid collisions. In this paper, we explore vulnerabilities of MDE algorithms in AD systems, presenting LensAttack, a novel physical attack that strategically places optical lenses on the camera of an autonomous vehicle to manipulate the perceived object depths. LensAttack encompasses two attack formats: concave lens attack and convex lens attack, each utilizing different optical lenses to induce false depth perception. We first develop a mathematical model that outlines the parameters of the attack, followed by simulations and real-world evaluations to assess its efficacy on state-of-the-art MDE models. Additionally, we adopt an attack optimization method to further enhance the attack success rate by optimizing the attack focal length. To better evaluate the implications of LensAttack on AD, we conduct comprehensive end-to-end system simulations using the CARLA platform. The results reveal that LensAttack can significantly disrupt the depth estimation processes in AD systems, posing a serious threat to their reliability and safety. Finally, we discuss some potential defense methods to mitigate the effects of the proposed attack.
Monocular metric depth estimation (MMDE) is a crucial task to solve for indoor scene reconstruction on edge devices. Despite this importance, existing models are sensitive to factors such as boundary frequency of objects in the scene and scene complexity, failing to fully capture many indoor scenes. In this work, we propose to close this gap through the task of monocular metric depth refinement (MMDR) by leveraging state-of-the-art MMDE models. MultiDepth proposes a solution by taking samples of the image along with the initial depth map prediction made by a pre-trained MMDE model. Compared to existing iterative depth refinement techniques, MultiDepth does not employ normal map prediction as part of its architecture, effectively lowering the model size and computation overhead while outputting impactful changes from refining iterations. MultiDepth implements a lightweight encoder-decoder architecture for the refinement network, processing multiple samples from the given image, including segmentation masking. We evaluate MultiDepth on four datasets and compare them to state-of-the-art methods to demonstrate its effective refinement with minimal overhead, displaying accuracy improvement upward of 45%.