PyTorchKR Papers

최신 논문

총 2,547편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2112.05498

Sparse Depth Completion with Semantic Mesh Deformation Optimization

Sparse depth measurements are widely available in many applications such as augmented reality, visual inertial odometry and robots equipped with low cost depth sensors. Although such sparse depth samples work well for certain applications like motion tracking, a complete depth map is usually preferred for broader applications, such as 3D object recognition, 3D reconstruction and autonomous driving. Despite the recent advancements in depth prediction from single RGB images with deeper neural networks, the existing approaches do not yield reliable results for practical use. In this work, we propose a neural network with post-optimization, which takes an RGB image and sparse depth samples as input and predicts the complete depth map. We make three major contributions to advance the state-of-the-art: an improved backbone network architecture named EDNet, a semantic edge-weighted loss function and a semantic mesh deformation optimization method. Our evaluation results outperform the existing work consistently on both indoor and outdoor datasets, and it significantly reduces the mean average error by up to 19.5% under the same settings of 200 sparse samples on NYU-Depth-V2 dataset.

arXiv:2112.05396

Towards Full-to-Empty Room Generation with Structure-Aware Feature Encoding and Soft Semantic Region-Adaptive Normalization

The task of transforming a furnished room image into a background-only is extremely challenging since it requires making large changes regarding the scene context while still preserving the overall layout and style. In order to acquire photo-realistic and structural consistent background, existing deep learning methods either employ image inpainting approaches or incorporate the learning of the scene layout as an individual task and leverage it later in a not fully differentiable semantic region-adaptive normalization module. To tackle these drawbacks, we treat scene layout generation as a feature linear transformation problem and propose a simple yet effective adjusted fully differentiable soft semantic region-adaptive normalization module (softSEAN) block. We showcase the applicability in diminished reality and depth estimation tasks, where our approach besides the advantages of mitigating training complexity and non-differentiability issues, surpasses the compared methods both quantitatively and qualitatively. Our softSEAN block can be used as a drop-in module for existing discriminative and generative models. Implementation is available on vcl3d.github.io/PanoDR/.

arXiv:2112.03325

Self-Supervised Camera Self-Calibration from Video

Camera calibration is integral to robotics and computer vision algorithms that seek to infer geometric properties of the scene from visual input streams. In practice, calibration is a laborious procedure requiring specialized data collection and careful tuning. This process must be repeated whenever the parameters of the camera change, which can be a frequent occurrence for mobile robots and autonomous vehicles. In contrast, self-supervised depth and ego-motion estimation approaches can bypass explicit calibration by inferring per-frame projection models that optimize a view synthesis objective. In this paper, we extend this approach to explicitly calibrate a wide range of cameras from raw videos in the wild. We propose a learning algorithm to regress per-sequence calibration parameters using an efficient family of general camera models. Our procedure achieves self-calibration results with sub-pixel reprojection error, outperforming other learning-based methods. We validate our approach on a wide variety of camera geometries, including perspective, fisheye, and catadioptric. Finally, we show that our approach leads to improvements in the downstream task of depth estimation, achieving state-of-the-art results on the EuRoC dataset with greater computational efficiency than contemporary methods.

arXiv:2112.03750

Wild ToFu: Improving Range and Quality of Indirect Time-of-Flight Depth with RGB Fusion in Challenging Environments

Indirect Time-of-Flight (I-ToF) imaging is a widespread way of depth estimation for mobile devices due to its small size and affordable price. Previous works have mainly focused on quality improvement for I-ToF imaging especially curing the effect of Multi Path Interference (MPI). These investigations are typically done in specifically constrained scenarios at close distance, indoors and under little ambient light. Surprisingly little work has investigated I-ToF quality improvement in real-life scenarios where strong ambient light and far distances pose difficulties due to an extreme amount of induced shot noise and signal sparsity, caused by the attenuation with limited sensor power and light scattering. In this work, we propose a new learning based end-to-end depth prediction network which takes noisy raw I-ToF signals as well as an RGB image and fuses their latent representation based on a multi step approach involving both implicit and explicit alignment to predict a high quality long range depth map aligned to the RGB viewpoint. We test our approach on challenging real-world scenes and show more than 40% RMSE improvement on the final depth map compared to the baseline approach.

arXiv:2112.03243

Input-level Inductive Biases for 3D Reconstruction

Much of the recent progress in 3D vision has been driven by the development of specialized architectures that incorporate geometrical inductive biases. In this paper we tackle 3D reconstruction using a domain agnostic architecture and study how instead to inject the same type of inductive biases directly as extra inputs to the model. This approach makes it possible to apply existing general models, such as Perceivers, on this rich domain, without the need for architectural changes, while simultaneously maintaining data efficiency of bespoke models. In particular we study how to encode cameras, projective ray incidence and epipolar geometry as model inputs, and demonstrate competitive multi-view depth estimation performance on multiple benchmarks.

arXiv:2112.03045

3D Hierarchical Refinement and Augmentation for Unsupervised Learning of Depth and Pose from Monocular Video

Depth and ego-motion estimations are essential for the localization and navigation of autonomous robots and autonomous driving. Recent studies make it possible to learn the per-pixel depth and ego-motion from the unlabeled monocular video. A novel unsupervised training framework is proposed with 3D hierarchical refinement and augmentation using explicit 3D geometry. In this framework, the depth and pose estimations are hierarchically and mutually coupled to refine the estimated pose layer by layer. The intermediate view image is proposed and synthesized by warping the pixels in an image with the estimated depth and coarse pose. Then, the residual pose transformation can be estimated from the new view image and the image of the adjacent frame to refine the coarse pose. The iterative refinement is implemented in a differentiable manner in this paper, making the whole framework optimized uniformly. Meanwhile, a new image augmentation method is proposed for the pose estimation by synthesizing a new view image, which creatively augments the pose in 3D space but gets a new augmented 2D image. The experiments on KITTI demonstrate that our depth estimation achieves state-of-the-art performance and even surpasses recent approaches that utilize other auxiliary tasks. Our visual odometry outperforms all recent unsupervised monocular learning-based methods and achieves competitive performance to the geometry-based method, ORB-SLAM2 with back-end optimization.

arXiv:2112.02582공식 코드 · Papers with Code

PolyphonicFormer: Unified Query Learning for Depth-aware Video Panoptic Segmentation

The Depth-aware Video Panoptic Segmentation (DVPS) is a new challenging vision problem that aims to predict panoptic segmentation and depth in a video simultaneously. The previous work solves this task by extending the existing panoptic segmentation method with an extra dense depth prediction and instance tracking head. However, the relationship between the depth and panoptic segmentation is not well explored -- simply combining existing methods leads to competition and needs carefully weight balancing. In this paper, we present PolyphonicFormer, a vision transformer to unify these sub-tasks under the DVPS task and lead to more robust results. Our principal insight is that the depth can be harmonized with the panoptic segmentation with our proposed new paradigm of predicting instance level depth maps with object queries. Then the relationship between the two tasks via query-based learning is explored. From the experiments, we demonstrate the benefits of our design from both depth estimation and panoptic segmentation aspects. Since each thing query also encodes the instance-wise information, it is natural to perform tracking directly with appearance learning. Our method achieves state-of-the-art results on two DVPS datasets (Semantic KITTI, Cityscapes), and ranks 1st on the ICCV-2021 BMTT Challenge video + depth track. Code is available at https://github.com/HarborYuan/PolyphonicFormer .

arXiv:2112.02416공식 코드 · Papers with Code

Gated2Gated: Self-Supervised Depth Estimation from Gated Images

Gated cameras hold promise as an alternative to scanning LiDAR sensors with high-resolution 3D depth that is robust to back-scatter in fog, snow, and rain. Instead of sequentially scanning a scene and directly recording depth via the photon time-of-flight, as in pulsed LiDAR sensors, gated imagers encode depth in the relative intensity of a handful of gated slices, captured at megapixel resolution. Although existing methods have shown that it is possible to decode high-resolution depth from such measurements, these methods require synchronized and calibrated LiDAR to supervise the gated depth decoder -- prohibiting fast adoption across geographies, training on large unpaired datasets, and exploring alternative applications outside of automotive use cases. In this work, we fill this gap and propose an entirely self-supervised depth estimation method that uses gated intensity profiles and temporal consistency as a training signal. The proposed model is trained end-to-end from gated video sequences, does not require LiDAR or RGB data, and learns to estimate absolute depth values. We take gated slices as input and disentangle the estimation of the scene albedo, depth, and ambient light, which are then used to learn to reconstruct the input slices through a cyclic loss. We rely on temporal consistency between a given frame and neighboring gated slices to estimate depth in regions with shadows and reflections. We experimentally validate that the proposed approach outperforms existing supervised and self-supervised depth estimation methods based on monocular RGB and stereo images, as well as supervised methods based on gated images.

arXiv:2112.02338공식 코드 · Papers with Code

Generalized Binary Search Network for Highly-Efficient Multi-View Stereo

Multi-view Stereo (MVS) with known camera parameters is essentially a 1D search problem within a valid depth range. Recent deep learning-based MVS methods typically densely sample depth hypotheses in the depth range, and then construct prohibitively memory-consuming 3D cost volumes for depth prediction. Although coarse-to-fine sampling strategies alleviate this overhead issue to a certain extent, the efficiency of MVS is still an open challenge. In this work, we propose a novel method for highly efficient MVS that remarkably decreases the memory footprint, meanwhile clearly advancing state-of-the-art depth prediction performance. We investigate what a search strategy can be reasonably optimal for MVS taking into account of both efficiency and effectiveness. We first formulate MVS as a binary search problem, and accordingly propose a generalized binary search network for MVS. Specifically, in each step, the depth range is split into 2 bins with extra 1 error tolerance bin on both sides. A classification is performed to identify which bin contains the true depth. We also design three mechanisms to respectively handle classification errors, deal with out-of-range samples and decrease the training memory. The new formulation makes our method only sample a very small number of depth hypotheses in each step, which is highly memory efficient, and also greatly facilitates quick training convergence. Experiments on competitive benchmarks show that our method achieves state-of-the-art accuracy with much less memory. Particularly, our method obtains an overall score of 0.289 on DTU dataset and tops the first place on challenging Tanks and Temples advanced dataset among all the learning-based methods. The trained models and code will be released at https://github.com/MiZhenxing/GBi-Net.

arXiv:2112.02306공식 코드 · Papers with Code

Toward Practical Monocular Indoor Depth Estimation

The majority of prior monocular depth estimation methods without groundtruth depth guidance focus on driving scenarios. We show that such methods generalize poorly to unseen complex indoor scenes, where objects are cluttered and arbitrarily arranged in the near field. To obtain more robustness, we propose a structure distillation approach to learn knacks from an off-the-shelf relative depth estimator that produces structured but metric-agnostic depth. By combining structure distillation with a branch that learns metrics from left-right consistency, we attain structured and metric depth for generic indoor scenes and make inferences in real-time. To facilitate learning and evaluation, we collect SimSIN, a dataset from simulation with thousands of environments, and UniSIN, a dataset that contains about 500 real scan sequences of generic indoor environments. We experiment in both sim-to-real and real-to-real settings, and show improvements, as well as in downstream applications using our depth maps. This work provides a full study, covering methods, data, and applications aspects.

arXiv:2112.01914공식 코드 · Papers with Code

SGM3D: Stereo Guided Monocular 3D Object Detection

Monocular 3D object detection aims to predict the object location, dimension and orientation in 3D space alongside the object category given only a monocular image. It poses a great challenge due to its ill-posed property which is critically lack of depth information in the 2D image plane. While there exist approaches leveraging off-the-shelve depth estimation or relying on LiDAR sensors to mitigate this problem, the dependence on the additional depth model or expensive equipment severely limits their scalability to generic 3D perception. In this paper, we propose a stereo-guided monocular 3D object detection framework, dubbed SGM3D, adapting the robust 3D features learned from stereo inputs to enhance the feature for monocular detection. We innovatively present a multi-granularity domain adaptation (MG-DA) mechanism to exploit the network's ability to generate stereo-mimicking features given only on monocular cues. Coarse BEV feature-level, as well as the fine anchor-level domain adaptation, are both leveraged for guidance in the monocular domain.In addition, we introduce an IoU matching-based alignment (IoU-MA) method for object-level domain adaptation between the stereo and monocular predictions to alleviate the mismatches while adopting the MG-DA. Extensive experiments demonstrate state-of-the-art results on KITTI and Lyft datasets.

arXiv:2112.01688

Machine Learning Subsystem for Autonomous Collision Avoidance on a small UAS with Embedded GPU

Interest in unmanned aerial system (UAS) powered solutions for 6G communication networks has grown immensely with the widespread availability of machine learning based autonomy modules and embedded graphical processing units (GPUs). While these technologies have revolutionized the possibilities of UAS solutions, designing an operable, robust autonomy framework for UAS remains a multi-faceted and difficult problem. In this work, we present our novel, modular framework for UAS autonomy, entitled MR-iFLY, and discuss how it may be extended to enable 6G swarm solutions. We begin by detailing the challenges associated with machine learning based UAS autonomy on resource constrained devices. Next, we describe in depth, how MR-iFLY's novel depth estimation and collision avoidance technology meets these challenges. Lastly, we describe the various evaluation criteria we have used to measure performance, show how our optimized machine vision components provide up to 15X speedup over baseline models and present a flight demonstration video of MR-iFLY's vision-based collision avoidance technology. We argue that these empirical results substantiate MR-iFLY as a candidate for use in reducing communication overhead between nodes in 6G communication swarms by providing standalone collision avoidance and navigation capabilities.

arXiv:2112.00821

FaSS-MVS -- Fast Multi-View Stereo with Surface-Aware Semi-Global Matching from UAV-borne Monocular Imagery

With FaSS-MVS, we present an approach for fast multi-view stereo with surface-aware Semi-Global Matching that allows for rapid depth and normal map estimation from monocular aerial video data captured by UAVs. The data estimated by FaSS-MVS, in turn, facilitates online 3D mapping, meaning that a 3D map of the scene is immediately and incrementally generated while the image data is acquired or being received. FaSS-MVS is comprised of a hierarchical processing scheme in which depth and normal data, as well as corresponding confidence scores, are estimated in a coarse-to-fine manner, allowing to efficiently process large scene depths which are inherent to oblique imagery captured by low-flying UAVs. The actual depth estimation employs a plane-sweep algorithm for dense multi-image matching to produce depth hypotheses from which the actual depth map is extracted by means of a surface-aware semi-global optimization, reducing the fronto-parallel bias of SGM. Given the estimated depth map, the pixel-wise surface normal information is then computed by reprojecting the depth map into a point cloud and calculating the normal vectors within a confined local neighborhood. In a thorough quantitative and ablative study we show that the accuracies of the 3D information calculated by FaSS-MVS is close to that of state-of-the-art approaches for offline multi-view stereo, with the error not even being one magnitude higher than that of COLMAP. At the same time, however, the average run-time of FaSS-MVS to estimate a single depth and normal map is less than 14 % of that of COLMAP, allowing to perform an online and incremental processing of Full-HD imagery at 1-2 Hz.

arXiv:2112.01521공식 코드 · Papers with Code

Object-aware Monocular Depth Prediction with Instance Convolutions

With the advent of deep learning, estimating depth from a single RGB image has recently received a lot of attention, being capable of empowering many different applications ranging from path planning for robotics to computational cinematography. Nevertheless, while the depth maps are in their entirety fairly reliable, the estimates around object discontinuities are still far from satisfactory. This can be contributed to the fact that the convolutional operator naturally aggregates features across object discontinuities, resulting in smooth transitions rather than clear boundaries. Therefore, in order to circumvent this issue, we propose a novel convolutional operator which is explicitly tailored to avoid feature aggregation of different object parts. In particular, our method is based on estimating per-part depth values by means of superpixels. The proposed convolutional operator, which we dub "Instance Convolution", then only considers each object part individually on the basis of the estimated superpixels. Our evaluation with respect to the NYUv2 as well as the iBims dataset clearly demonstrates the superiority of Instance Convolutions over the classical convolution at estimating depth around occlusion boundaries, while producing comparable results elsewhere. Code will be made publicly available upon acceptance.

arXiv:2112.01517

Efficient Neural Radiance Fields for Interactive Free-viewpoint Video

This paper aims to tackle the challenge of efficiently producing interactive free-viewpoint videos. Some recent works equip neural radiance fields with image encoders, enabling them to generalize across scenes. When processing dynamic scenes, they can simply treat each video frame as an individual scene and perform novel view synthesis to generate free-viewpoint videos. However, their rendering process is slow and cannot support interactive applications. A major factor is that they sample lots of points in empty space when inferring radiance fields. We propose a novel scene representation, called ENeRF, for the fast creation of interactive free-viewpoint videos. Specifically, given multi-view images at one frame, we first build the cascade cost volume to predict the coarse geometry of the scene. The coarse geometry allows us to sample few points near the scene surface, thereby significantly improving the rendering speed. This process is fully differentiable, enabling us to jointly learn the depth prediction and radiance field networks from RGB images. Experiments on multiple benchmarks show that our approach exhibits competitive performance while being at least 60 times faster than previous generalizable radiance field methods.

arXiv:2112.01502

Dimensions of Motion: Monocular Prediction through Flow Subspaces

We introduce a way to learn to estimate a scene representation from a single image by predicting a low-dimensional subspace of optical flow for each training example, which encompasses the variety of possible camera and object movement. Supervision is provided by a novel loss which measures the distance between this predicted flow subspace and an observed optical flow. This provides a new approach to learning scene representation tasks, such as monocular depth prediction or instance segmentation, in an unsupervised fashion using in-the-wild input videos without requiring camera poses, intrinsics, or an explicit multi-view stereo step. We evaluate our method in multiple settings, including an indoor depth prediction task where it achieves comparable performance to recent methods trained with more supervision.

arXiv:2112.00432공식 코드 · Papers with Code

A benchmark with decomposed distribution shifts for 360 monocular depth estimation

In this work we contribute a distribution shift benchmark for a computer vision task; monocular depth estimation. Our differentiation is the decomposition of the wider distribution shift of uncontrolled testing on in-the-wild data, to three distinct distribution shifts. Specifically, we generate data via synthesis and analyze them to produce covariate (color input), prior (depth output) and concept (their relationship) distribution shifts. We also synthesize combinations and show how each one is indeed a different challenge to address, as stacking them produces increased performance drops and cannot be addressed horizontally using standard approaches.

arXiv:2112.00202공식 코드 · Papers with Code

3DVNet: Multi-View Depth Prediction and Volumetric Refinement

We present 3DVNet, a novel multi-view stereo (MVS) depth-prediction method that combines the advantages of previous depth-based and volumetric MVS approaches. Our key idea is the use of a 3D scene-modeling network that iteratively updates a set of coarse depth predictions, resulting in highly accurate predictions which agree on the underlying scene geometry. Unlike existing depth-prediction techniques, our method uses a volumetric 3D convolutional neural network (CNN) that operates in world space on all depth maps jointly. The network can therefore learn meaningful scene-level priors. Furthermore, unlike existing volumetric MVS techniques, our 3D CNN operates on a feature-augmented point cloud, allowing for effective aggregation of multi-view information and flexible iterative refinement of depth maps. Experimental results show our method exceeds state-of-the-art accuracy in both depth prediction and 3D reconstruction metrics on the ScanNet dataset, as well as a selection of scenes from the TUM-RGBD and ICL-NUIM datasets. This shows that our method is both effective and generalizes to new settings.

arXiv:2111.15669

360MonoDepth: High-Resolution 360° Monocular Depth Estimation

360{\deg} cameras can capture complete environments in a single shot, which makes 360{\deg} imagery alluring in many computer vision tasks. However, monocular depth estimation remains a challenge for 360{\deg} data, particularly for high resolutions like 2K (2048x1024) and beyond that are important for novel-view synthesis and virtual reality applications. Current CNN-based methods do not support such high resolutions due to limited GPU memory. In this work, we propose a flexible framework for monocular depth estimation from high-resolution 360{\deg} images using tangent images. We project the 360{\deg} input image onto a set of tangent planes that produce perspective views, which are suitable for the latest, most accurate state-of-the-art perspective monocular depth estimators. To achieve globally consistent disparity estimates, we recombine the individual depth estimates using deformable multi-scale alignment followed by gradient-domain blending. The result is a dense, high-resolution 360{\deg} depth map with a high level of detail, also for outdoor scenes which are not supported by existing methods. Our source code and data are available at https://manurare.github.io/360monodepth/.

arXiv:2111.15234

NeRFReN: Neural Radiance Fields with Reflections

Neural Radiance Fields (NeRF) has achieved unprecedented view synthesis quality using coordinate-based neural scene representations. However, NeRF's view dependency can only handle simple reflections like highlights but cannot deal with complex reflections such as those from glass and mirrors. In these scenarios, NeRF models the virtual image as real geometries which leads to inaccurate depth estimation, and produces blurry renderings when the multi-view consistency is violated as the reflected objects may only be seen under some of the viewpoints. To overcome these issues, we introduce NeRFReN, which is built upon NeRF to model scenes with reflections. Specifically, we propose to split a scene into transmitted and reflected components, and model the two components with separate neural radiance fields. Considering that this decomposition is highly under-constrained, we exploit geometric priors and apply carefully-designed training strategies to achieve reasonable decomposition results. Experiments on various self-captured scenes show that our method achieves high-quality novel view synthesis and physically sound depth estimation results while enabling scene editing applications.