Research on multi-view stereo based on remote sensing images has promoted the development of large-scale urban 3D reconstruction. However, remote sensing multi-view image data suffers from the problems of occlusion and uneven brightness between views during acquisition, which leads to the problem of blurred details in depth estimation. To solve the above problem, we re-examine the deformable learning method in the Multi-View Stereo task and propose a novel paradigm based on view Space and Depth deformable Learning (SDL-MVS), aiming to learn deformable interactions of features in different view spaces and deformably model the depth ranges and intervals to enable high accurate depth estimation. Specifically, to solve the problem of view noise caused by occlusion and uneven brightness, we propose a Progressive Space deformable Sampling (PSS) mechanism, which performs deformable learning of sampling points in the 3D frustum space and the 2D image space in a progressive manner to embed source features to the reference feature adaptively. To further optimize the depth, we introduce Depth Hypothesis deformable Discretization (DHD), which achieves precise positioning of the depth prior by adaptively adjusting the depth range hypothesis and performing deformable discretization of the depth interval hypothesis. Finally, our SDL-MVS achieves explicit modeling of occlusion and uneven brightness faced in multi-view stereo through the deformable learning paradigm of view space and depth, achieving accurate multi-view depth estimation. Extensive experiments on LuoJia-MVS and WHU datasets show that our SDL-MVS reaches state-of-the-art performance. It is worth noting that our SDL-MVS achieves an MAE error of 0.086, an accuracy of 98.9% for <0.6m, and 98.9% for <3-interval on the LuoJia-MVS dataset under the premise of three views as input.
Surround-view depth estimation is a crucial task aims to acquire the depth maps of the surrounding views. It has many applications in real world scenarios such as autonomous driving, AR/VR and 3D reconstruction, etc. However, given that most of the data in the autonomous driving dataset is collected in daytime scenarios, this leads to poor depth model performance in the face of out-of-distribution(OoD) data. While some works try to improve the robustness of depth model under OoD data, these methods either require additional training data or lake generalizability. In this report, we introduce the DINO-SD, a novel surround-view depth estimation model. Our DINO-SD does not need additional data and has strong robustness. Our DINO-SD get the best performance in the track4 of ICRA 2024 RoboDepth Challenge.
There has been a recent surge of interest in learning to perceive depth from monocular videos in an unsupervised fashion. A key challenge in this field is achieving robust and accurate depth estimation in challenging scenarios, particularly in regions with weak textures or where dynamic objects are present. This study makes three major contributions by delving deeply into dense correspondence priors to provide existing frameworks with explicit geometric constraints. The first novelty is a contextual-geometric depth consistency loss, which employs depth maps triangulated from dense correspondences based on estimated ego-motion to guide the learning of depth perception from contextual information, since explicitly triangulated depth maps capture accurate relative distances among pixels. The second novelty arises from the observation that there exists an explicit, deducible relationship between optical flow divergence and depth gradient. A differential property correlation loss is, therefore, designed to refine depth estimation with a specific emphasis on local variations. The third novelty is a bidirectional stream co-adjustment strategy that enhances the interaction between rigid and optical flows, encouraging the former towards more accurate correspondence and making the latter more adaptable across various scenarios under the static scene hypotheses. DCPI-Depth, a framework that incorporates all these innovative components and couples two bidirectional and collaborative streams, achieves state-of-the-art performance and generalizability across multiple public datasets, outperforming all existing prior arts. Specifically, it demonstrates accurate depth estimation in texture-less and dynamic regions, and shows more reasonable smoothness. Our source code will be publicly available at mias.group/DCPI-Depth upon publication.
In the field of 3D object detection tasks, fusing heterogeneous features from LiDAR and camera sensors into a unified Bird's Eye View (BEV) representation is a widely adopted paradigm. However, existing methods are often compromised by imprecise sensor calibration, resulting in feature misalignment in LiDAR-camera BEV fusion. Moreover, such inaccuracies result in errors in depth estimation for the camera branch, ultimately causing misalignment between LiDAR and camera BEV features. In this work, we propose a novel ContrastAlign approach that utilizes contrastive learning to enhance the alignment of heterogeneous modalities, thereby improving the robustness of the fusion process. Specifically, our approach includes the L-Instance module, which directly outputs LiDAR instance features within LiDAR BEV features. Then, we introduce the C-Instance module, which predicts camera instance features through RoI (Region of Interest) pooling on the camera BEV features. We propose the InstanceFusion module, which utilizes contrastive learning to generate similar instance features across heterogeneous modalities. We then use graph matching to calculate the similarity between the neighboring camera instance features and the similarity instance features to complete the alignment of instance features. Our method achieves state-of-the-art performance, with an mAP of 70.3%, surpassing BEVFusion by 1.8% on the nuScenes validation set. Importantly, our method outperforms BEVFusion by 7.3% under conditions with misalignment noise.
Recent advancements in bird's eye view (BEV) representations have shown remarkable promise for in-vehicle 3D perception. However, while these methods have achieved impressive results on standard benchmarks, their robustness in varied conditions remains insufficiently assessed. In this study, we present RoboBEV, an extensive benchmark suite designed to evaluate the resilience of BEV algorithms. This suite incorporates a diverse set of camera corruption types, each examined over three severity levels. Our benchmarks also consider the impact of complete sensor failures that occur when using multi-modal models. Through RoboBEV, we assess 33 state-of-the-art BEV-based perception models spanning tasks like detection, map segmentation, depth estimation, and occupancy prediction. Our analyses reveal a noticeable correlation between the model's performance on in-distribution datasets and its resilience to out-of-distribution challenges. Our experimental results also underline the efficacy of strategies like pre-training and depth-free BEV transformations in enhancing robustness against out-of-distribution data. Furthermore, we observe that leveraging extensive temporal information significantly improves the model's robustness. Based on our observations, we design an effective robustness enhancement strategy based on the CLIP model. The insights from this study pave the way for the development of future BEV models that seamlessly combine accuracy with real-world robustness.
We propose a method for depth estimation under different illumination conditions, i.e., day and night time. As photometry is uninformative in regions under low-illumination, we tackle the problem through a multi-sensor fusion approach, where we take as input an additional synchronized sparse point cloud (i.e., from a LiDAR) projected onto the image plane as a sparse depth map, along with a camera image. The crux of our method lies in the use of the abundantly available synthetic data to first approximate the 3D scene structure by learning a mapping from sparse to (coarse) dense depth maps along with their predictive uncertainty - we term this, SpaDe. In poorly illuminated regions where photometric intensities do not afford the inference of local shape, the coarse approximation of scene depth serves as a prior; the uncertainty map is then used with the image to guide refinement through an uncertainty-driven residual learning (URL) scheme. The resulting depth completion network leverages complementary strengths from both modalities - depth is sparse but insensitive to illumination and in metric scale, and image is dense but sensitive with scale ambiguity. SpaDe can be used in a plug-and-play fashion, which allows for 25% improvement when augmented onto existing methods to preprocess sparse depth. We demonstrate URL on the nuScenes dataset where we improve over all baselines by an average 11.65% in all-day scenarios, 11.23% when tested specifically for daytime, and 13.12% for nighttime scenes.
Deep neural networks excel in perception tasks such as semantic segmentation and monocular depth estimation, making them indispensable in safety-critical applications like autonomous driving and industrial inspection. However, they often suffer from overconfidence and poor explainability, especially for out-of-domain data. While uncertainty quantification has emerged as a promising solution to these challenges, multi-task settings have yet to be explored. In an effort to shed light on this, we evaluate Monte Carlo Dropout, Deep Sub-Ensembles, and Deep Ensembles for joint semantic segmentation and monocular depth estimation. Thereby, we reveal that Deep Ensembles stand out as the preferred choice, particularly in out-of-domain scenarios, and show the potential benefit of multi-task learning with regard to the uncertainty quality in comparison to solving both tasks separately. Additionally, we highlight the impact of employing different uncertainty thresholds to classify pixels as certain or uncertain, with the median uncertainty emerging as a robust default.
Disconnectivity and distortion are the two problems which must be coped with when processing 360 degrees equirectangular images. In this paper, we propose a method of estimating the depth of monocular panoramic image with a teacher-student model fusing equirectangular and spherical representations. In contrast with the existing methods fusing an equirectangular representation with a cube map representation or tangent representation, a spherical representation is a better choice because a sampling on a sphere is more uniform and can also cope with distortion more effectively. In this processing, a novel spherical convolution kernel computing with sampling points on a sphere is developed to extract features from the spherical representation, and then, a Segmentation Feature Fusion(SFF) methodology is utilized to combine the features with ones extracted from the equirectangular representation. In contrast with the existing methods using a teacher-student model to obtain a lighter model of depth estimation, we use a teacher-student model to learn the latent features of depth images. This results in a trained model which estimates the depth map of an equirectangular image using not only the feature maps extracted from an input equirectangular image but also the distilled knowledge learnt from the ground truth of depth map of a training set. In experiments, the proposed method is tested on several well-known 360 monocular depth estimation benchmark datasets, and outperforms the existing methods for the most evaluation indexes.
The perception of transparent objects for grasp and manipulation remains a major challenge, because existing robotic grasp methods which heavily rely on depth maps are not suitable for transparent objects due to their unique visual properties. These properties lead to gaps and inaccuracies in the depth maps of the transparent objects captured by depth sensors. To address this issue, we propose an end-to-end network for transparent object depth completion that combines the strengths of single-view RGB-D based depth completion and multi-view depth estimation. Moreover, we introduce a depth refinement module based on confidence estimation to fuse predicted depth maps from single-view and multi-view modules, which further refines the restored depth map. The extensive experiments on the ClearPose and TransCG datasets demonstrate that our method achieves superior accuracy and robustness in complex scenarios with significant occlusion compared to the state-of-the-art methods.
Monocular 3D object detection has vast application potential across various fields. DETR-type models have shown remarkable performance in different areas, but there is still considerable room for improvement in monocular 3D detection, especially with the existing DETR-based method, MonoDETR. After addressing the query initialization issues in MonoDETR, we explored several performance enhancement strategies, such as incorporating a more efficient encoder and utilizing a more powerful depth estimator. Ultimately, we proposed MonoDETRNext, a model that comes in two variants based on the choice of depth estimator: MonoDETRNext-E, which prioritizes speed, and MonoDETRNext-A, which focuses on accuracy. We posit that MonoDETRNext establishes a new benchmark in monocular 3D object detection and opens avenues for future research. We conducted an exhaustive evaluation demonstrating the model's superior performance against existing solutions. Notably, MonoDETRNext-A demonstrated a 3.52$\%$ improvement in the $AP_{3D}$ metric on the KITTI test benchmark over MonoDETR, while MonoDETRNext-E showed a 2.35$\%$ increase. Additionally, the computational efficiency of MonoDETRNext-E slightly exceeds that of its predecessor.
Event cameras offer promising advantages such as high dynamic range and low latency, making them well-suited for challenging lighting conditions and fast-moving scenarios. However, reconstructing 3D scenes from raw event streams is difficult because event data is sparse and does not carry absolute color information. To release its potential in 3D reconstruction, we propose the first event-based generalizable 3D reconstruction framework, called EvGGS, which reconstructs scenes as 3D Gaussians from only event input in a feedforward manner and can generalize to unseen cases without any retraining. This framework includes a depth estimation module, an intensity reconstruction module, and a Gaussian regression module. These submodules connect in a cascading manner, and we collaboratively train them with a designed joint loss to make them mutually promote. To facilitate related studies, we build a novel event-based 3D dataset with various material objects and calibrated labels of grayscale images, depth maps, camera poses, and silhouettes. Experiments show models that have jointly trained significantly outperform those trained individually. Our approach performs better than all baselines in reconstruction quality, and depth/intensity predictions with satisfactory rendering speed.
Depth estimation based on stereo matching is a classic but popular computer vision problem, which has a wide range of real-world applications. Current stereo matching methods generally adopt the deep Siamese neural network architecture, and have achieved impressing performance by constructing feature matching cost volumes and using 3D convolutions for cost aggregation. However, most existing methods suffer from large number of parameters and slow running time due to the sequential use of 3D convolutions. In this paper, we propose Ghost-Stereo, a novel end-to-end stereo matching network. The feature extraction part of the network uses the GhostNet to form a U-shaped structure. The core of Ghost-Stereo is a GhostNet feature-based cost volume enhancement (Ghost-CVE) module and a GhostNet-inspired lightweight cost volume aggregation (Ghost-CVA) module. For the Ghost-CVE part, cost volumes are constructed and fused by the GhostNet-based features to enhance the spatial context awareness. For the Ghost-CVA part, a lightweight 3D convolution bottleneck block based on the GhostNet is proposed to reduce the computational complexity in this module. By combining with the context and geometry fusion module, a classical hourglass-shaped cost volume aggregate structure is constructed. Ghost-Stereo achieves a comparable performance than state-of-the-art real-time methods on several publicly benchmarks, and shows a better generalization ability.
RGB-D tracking significantly improves the accuracy of object tracking. However, its dependency on real depth inputs and the complexity involved in multi-modal fusion limit its applicability across various scenarios. The utilization of depth information in RGB-D tracking inspired us to propose a new method, named MDETrack, which trains a tracking network with an additional capability to understand the depth of scenes, through supervised or self-supervised auxiliary Monocular Depth Estimation learning. The outputs of MDETrack's unified feature extractor are fed to the side-by-side tracking head and auxiliary depth estimation head, respectively. The auxiliary module will be discarded in inference, thus keeping the same inference speed. We evaluated our models with various training strategies on multiple datasets, and the results show an improved tracking accuracy even without real depth. Through these findings we highlight the potential of depth estimation in enhancing object tracking performance.
Gated cameras flood-illuminate a scene and capture the time-gated impulse response of a scene. By employing nanosecond-scale gates, existing sensors are capable of capturing mega-pixel gated images, delivering dense depth improving on today's LiDAR sensors in spatial resolution and depth precision. Although gated depth estimation methods deliver a million of depth estimates per frame, their resolution is still an order below existing RGB imaging methods. In this work, we combine high-resolution stereo HDR RCCB cameras with gated imaging, allowing us to exploit depth cues from active gating, multi-view RGB and multi-view NIR sensing -- multi-view and gated cues across the entire spectrum. The resulting capture system consists only of low-cost CMOS sensors and flood-illumination. We propose a novel stereo-depth estimation method that is capable of exploiting these multi-modal multi-view depth cues, including the active illumination that is measured by the RCCB camera when removing the IR-cut filter. The proposed method achieves accurate depth at long ranges, outperforming the next best existing method by 39% for ranges of 100 to 220m in MAE on accumulated LiDAR ground-truth. Our code, models and datasets are available at https://light.princeton.edu/gatedrccbstereo/ .
Self-supervised depth estimation algorithms rely heavily on frame-warping relationships, exhibiting substantial performance degradation when applied in challenging circumstances, such as low-visibility and nighttime scenarios with varying illumination conditions. Addressing this challenge, we introduce an algorithm designed to achieve accurate self-supervised stereo depth estimation focusing on nighttime conditions. Specifically, we use pretrained visual foundation models to extract generalised features across challenging scenes and present an efficient method for matching and integrating these features from stereo frames. Moreover, to prevent pixels violating photometric consistency assumption from negatively affecting the depth predictions, we propose a novel masking approach designed to filter out such pixels. Lastly, addressing weaknesses in the evaluation of current depth estimation algorithms, we present novel evaluation metrics. Our experiments, conducted on challenging datasets including Oxford RobotCar and Multi-Spectral Stereo, demonstrate the robust improvements realized by our approach. Code is available at: https://github.com/madhubabuv/dtd
We introduce a novel depth estimation technique for multi-frame structured light setups using neural implicit representations of 3D space. Our approach employs a neural signed distance field (SDF), trained through self-supervised differentiable rendering. Unlike passive vision, where joint estimation of radiance and geometry fields is necessary, we capitalize on known radiance fields from projected patterns in structured light systems. This enables isolated optimization of the geometry field, ensuring convergence and network efficacy with fixed device positioning. To enhance geometric fidelity, we incorporate an additional color loss based on object surfaces during training. Real-world experiments demonstrate our method's superiority in geometric performance for few-shot scenarios, while achieving comparable results with increased pattern availability.
Dense depth maps have been used as a key element of visual perception tasks. There have been tremendous efforts to enhance the depth quality, ranging from optimization-based to learning-based methods. Despite the remarkable progress for a long time, their applicability in the real world is limited due to systematic measurement biases such as density, sensing pattern, and scan range. It is well-known that the biases make it difficult for these methods to achieve their generalization. We observe that learning a joint representation for input modalities (e.g., images and depth), which most recent methods adopt, is sensitive to the biases. In this work, we disentangle those modalities to mitigate the biases with prompt engineering. For this, we design a novel depth prompt module to allow the desirable feature representation according to new depth distributions from either sensor types or scene configurations. Our depth prompt can be embedded into foundation models for monocular depth estimation. Through this embedding process, our method helps the pretrained model to be free from restraint of depth scan range and to provide absolute scale depth maps. We demonstrate the effectiveness of our method through extensive evaluations. Source code is publicly available at https://github.com/JinhwiPark/DepthPrompting .
Monocular 360 depth estimation is challenging due to the inherent distortion of the equirectangular projection (ERP). This distortion causes a problem: spherical adjacent points are separated after being projected to the ERP plane, particularly in the polar regions. To tackle this problem, recent methods calculate the spherical neighbors in the tangent domain. However, as the tangent patch and sphere only have one common point, these methods construct neighboring spherical relationships around the common point. In this paper, we propose spherical fully-connected CRFs (SF-CRFs). We begin by evenly partitioning an ERP image with regular windows, where windows at the equator involve broader spherical neighbors than those at the poles. To improve the spherical relationships, our SF-CRFs enjoy two key components. Firstly, to involve sufficient spherical neighbors, we propose a Spherical Window Transform (SWT) module. This module aims to replicate the equator window's spherical relationships to all other windows, leveraging the rotational invariance of the sphere. Remarkably, the transformation process is highly efficient, completing the transformation of all windows in a 512X1024 ERP with 0.038 seconds on CPU. Secondly, we propose a Planar-Spherical Interaction (PSI) module to facilitate the relationships between regular and transformed windows, which not only preserves the local details but also captures global structures. By building a decoder based on the SF-CRFs blocks, we propose CRF360D, a novel 360 depth estimation framework that achieves state-of-the-art performance across diverse datasets. Our CRF360D is compatible with different perspective image-trained backbones (e.g., EfficientNet), serving as the encoder.
Most existing methods often rely on complex models to predict scene depth with high accuracy, resulting in slow inference that is not conducive to deployment. To better balance precision and speed, we first designed SmallDepth based on sparsity. Second, to enhance the feature representation ability of SmallDepth during training under the condition of equal complexity during inference, we propose an equivalent transformation module(ETM). Third, to improve the ability of each layer in the case of a fixed SmallDepth to perceive different context information and improve the robustness of SmallDepth to the left-right direction and illumination changes, we propose pyramid loss. Fourth, to further improve the accuracy of SmallDepth, we utilized the proposed function approximation loss (APX) to transfer knowledge in the pretrained HQDecv2, obtained by optimizing the previous HQDec to address grid artifacts in some regions, to SmallDepth. Extensive experiments demonstrate that each proposed component improves the precision of SmallDepth without changing the complexity of SmallDepth during inference, and the developed approach achieves state-of-the-art results on KITTI at an inference speed of more than 500 frames per second and with approximately 2 M parameters. The code and models will be publicly available at https://github.com/fwucas/FA-Depth.
3D occupancy perception holds a pivotal role in recent vision-centric autonomous driving systems by converting surround-view images into integrated geometric and semantic representations within dense 3D grids. Nevertheless, current models still encounter two main challenges: modeling depth accurately in the 2D-3D view transformation stage, and overcoming the lack of generalizability issues due to sparse LiDAR supervision. To address these issues, this paper presents GEOcc, a Geometric-Enhanced Occupancy network tailored for vision-only surround-view perception. Our approach is three-fold: 1) Integration of explicit lift-based depth prediction and implicit projection-based transformers for depth modeling, enhancing the density and robustness of view transformation. 2) Utilization of mask-based encoder-decoder architecture for fine-grained semantic predictions; 3) Adoption of context-aware self-training loss functions in the pertaining stage to complement LiDAR supervision, involving the re-rendering of 2D depth maps from 3D occupancy features and leveraging image reconstruction loss to obtain denser depth supervision besides sparse LiDAR ground-truths. Our approach achieves State-Of-The-Art performance on the Occ3D-nuScenes dataset with the least image resolution needed and the most weightless image backbone compared with current models, marking an improvement of 3.3% due to our proposed contributions. Comprehensive experimentation also demonstrates the consistent superiority of our method over baselines and alternative approaches.