Automating leaf manipulation in agricultural settings faces significant challenges, including the variability of plant morphologies and deformable leaves. We propose a novel hybrid geometric-neural approach for autonomous leaf grasping that combines traditional computer vision with neural networks through self-supervised learning. Our method integrates YOLOv8 for instance segmentation and RAFT-Stereo for 3D depth estimation to build rich leaf representations, which feed into both a geometric feature scoring pipeline and a neural refinement module (GraspPointCNN). The key innovation is our confidence-weighted fusion mechanism that dynamically balances the contribution of each approach based on prediction certainty. Our self-supervised framework uses the geometric pipeline as an expert teacher to automatically generate training data. Experiments demonstrate that our approach achieves an 88.0% success rate in controlled environments and 84.7% in real greenhouse conditions, significantly outperforming both purely geometric (75.3%) and neural (60.2%) methods. This work establishes a new paradigm for agricultural robotics where domain expertise is seamlessly integrated with machine learning capabilities, providing a foundation for fully automated crop monitoring systems.
Due to advancements in infrastructural modulations, architectural design is one of the most peculiar and tedious processes. As the technology evolves to the next phase, using some latest techniques like generative adversarial networks, creating a hybrid architectural design from old and new models is possible with maximum accuracy. Training the model with appropriate samples makes it evident that the designing phase will be simple for even a layman by including proper parameters such as material description, structural engineering, etc. This research paper suggests a hybrid model for an architectural design using generative adversarial networks. For example, merging Rome's architectural style with Italy's will accurately and precisely recover the pixel-level structure of 3D forms without needing a 2D viewpoint or 3D annotations from a real 2D generated image.
Neural Radiance Field (NeRF) research has attracted significant attention recently, with 3D modelling, virtual/augmented reality, and visual effects driving its application. While current NeRF implementations can produce high quality visual results, there is a conspicuous lack of reliable methods for evaluating them. Conventional image quality assessment methods and analytical metrics (e.g. PSNR, SSIM, LPIPS etc.) only provide approximate indicators of performance since they generalise the ability of the entire NeRF pipeline. Hence, in this paper, we propose a new test framework which isolates the neural rendering network from the NeRF pipeline and then performs a parametric evaluation by training and evaluating the NeRF on an explicit radiance field representation. We also introduce a configurable approach for generating representations specifically for evaluation purposes. This employs ray-casting to transform mesh models into explicit NeRF samples, as well as to "shade" these representations. Combining these two approaches, we demonstrate how different "tasks" (scenes with different visual effects or learning strategies) and types of networks (NeRFs and depth-wise implicit neural representations (INRs)) can be evaluated within this framework. Additionally, we propose a novel metric to measure task complexity of the framework which accounts for the visual parameters and the distribution of the spatial data. Our approach offers the potential to create a comparative objective evaluation framework for NeRF methods.
This work introduces a new approach for joint detection of centerlines based on image data by localizing the features jointly in 2D and 3D. In contrast to existing work that focuses on detection of visual cues, we explore feature extraction methods that are directly amenable to the urban driving task. To develop and evaluate our approach, a large urban driving dataset dubbed AV Breadcrumbs is automatically labeled by leveraging vector map representations and projective geometry to annotate over 900,000 images. Our results demonstrate potential for dynamic scene modeling across various urban driving scenarios. Our model achieves an F1 score of 0.684 and an average normalized depth error of 2.083. The code and data annotations are publicly available.
Given an image with multiple people, our goal is to directly regress the pose and shape of all the people as well as their relative depth. Inferring the depth of a person in an image, however, is fundamentally ambiguous without knowing their height. This is particularly problematic when the scene contains people of very different sizes, e.g. from infants to adults. To solve this, we need several things. First, we develop a novel method to infer the poses and depth of multiple people in a single image. While previous work that estimates multiple people does so by reasoning in the image plane, our method, called BEV, adds an additional imaginary Bird's-Eye-View representation to explicitly reason about depth. BEV reasons simultaneously about body centers in the image and in depth and, by combing these, estimates 3D body position. Unlike prior work, BEV is a single-shot method that is end-to-end differentiable. Second, height varies with age, making it impossible to resolve depth without also estimating the age of people in the image. To do so, we exploit a 3D body model space that lets BEV infer shapes from infants to adults. Third, to train BEV, we need a new dataset. Specifically, we create a "Relative Human" (RH) dataset that includes age labels and relative depth relationships between the people in the images. Extensive experiments on RH and AGORA demonstrate the effectiveness of the model and training scheme. BEV outperforms existing methods on depth reasoning, child shape estimation, and robustness to occlusion. The code and dataset are released for research purposes.
This paper focuses on the regression of multiple 3D people from a single RGB image. Existing approaches predominantly follow a multi-stage pipeline that first detects people in bounding boxes and then independently regresses their 3D body meshes. In contrast, we propose to Regress all meshes in a One-stage fashion for Multiple 3D People (termed ROMP). The approach is conceptually simple, bounding box-free, and able to learn a per-pixel representation in an end-to-end manner. Our method simultaneously predicts a Body Center heatmap and a Mesh Parameter map, which can jointly describe the 3D body mesh on the pixel level. Through a body-center-guided sampling process, the body mesh parameters of all people in the image are easily extracted from the Mesh Parameter map. Equipped with such a fine-grained representation, our one-stage framework is free of the complex multi-stage process and more robust to occlusion. Compared with state-of-the-art methods, ROMP achieves superior performance on the challenging multi-person benchmarks, including 3DPW and CMU Panoptic. Experiments on crowded/occluded datasets demonstrate the robustness under various types of occlusion. The released code is the first real-time implementation of monocular multi-person 3D mesh regression.
Recovering multi-person 3D poses with absolute scales from a single RGB image is a challenging problem due to the inherent depth and scale ambiguity from a single view. Addressing this ambiguity requires to aggregate various cues over the entire image, such as body sizes, scene layouts, and inter-person relationships. However, most previous methods adopt a top-down scheme that first performs 2D pose detection and then regresses the 3D pose and scale for each detected person individually, ignoring global contextual cues. In this paper, we propose a novel system that first regresses a set of 2.5D representations of body parts and then reconstructs the 3D absolute poses based on these 2.5D representations with a depth-aware part association algorithm. Such a single-shot bottom-up scheme allows the system to better learn and reason about the inter-person depth relationship, improving both 3D and 2D pose estimation. The experiments demonstrate that the proposed approach achieves the state-of-the-art performance on the CMU Panoptic and MuPoTS-3D datasets and is applicable to in-the-wild videos.
In this work, we address the problem of multi-person 3D pose estimation from a single image. A typical regression approach in the top-down setting of this problem would first detect all humans and then reconstruct each one of them independently. However, this type of prediction suffers from incoherent results, e.g., interpenetration and inconsistent depth ordering between the people in the scene. Our goal is to train a single network that learns to avoid these problems and generate a coherent 3D reconstruction of all the humans in the scene. To this end, a key design choice is the incorporation of the SMPL parametric body model in our top-down framework, which enables the use of two novel losses. First, a distance field-based collision loss penalizes interpenetration among the reconstructed people. Second, a depth ordering-aware loss reasons about occlusions and promotes a depth ordering of people that leads to a rendering which is consistent with the annotated instance segmentation. This provides depth supervision signals to the network, even if the image has no explicit 3D annotations. The experiments show that our approach outperforms previous methods on standard 3D pose benchmarks, while our proposed losses enable more coherent reconstruction in natural images. The project website with videos, results, and code can be found at: https://jiangwenpl.github.io/multiperson
Reliable and accurate 3D object detection is a necessity for safe autonomous driving. Although LiDAR sensors can provide accurate 3D point cloud estimates of the environment, they are also prohibitively expensive for many settings. Recently, the introduction of pseudo-LiDAR (PL) has led to a drastic reduction in the accuracy gap between methods based on LiDAR sensors and those based on cheap stereo cameras. PL combines state-of-the-art deep neural networks for 3D depth estimation with those for 3D object detection by converting 2D depth map outputs to 3D point cloud inputs. However, so far these two networks have to be trained separately. In this paper, we introduce a new framework based on differentiable Change of Representation (CoR) modules that allow the entire PL pipeline to be trained end-to-end. The resulting framework is compatible with most state-of-the-art networks for both tasks and in combination with PointRCNN improves over PL consistently across all benchmarks -- yielding the highest entry on the KITTI image-based 3D object detection leaderboard at the time of submission. Our code will be made available at https://github.com/mileyan/pseudo-LiDAR_e2e.
Learning based approaches for depth perception are limited by the availability of clean training data. This has led to the utilization of view synthesis as an indirect objective for learning depth estimation using efficient data acquisition procedures. Nonetheless, most research focuses on pinhole based monocular vision, with scarce works presenting results for omnidirectional input. In this work, we explore spherical view synthesis for learning monocular 360 depth in a self-supervised manner and demonstrate its feasibility. Under a purely geometrically derived formulation we present results for horizontal and vertical baselines, as well as for the trinocular case. Further, we show how to better exploit the expressiveness of traditional CNNs when applied to the equirectangular domain in an efficient manner. Finally, given the availability of ground truth depth data, our work is uniquely positioned to compare view synthesis against direct supervision in a consistent and fair manner. The results indicate that alternative research directions might be better suited to enable higher quality depth perception. Our data, models and code are publicly available at https://vcl3d.github.io/SphericalViewSynthesis/.
The 3D depth estimation and relative pose estimation problem within a decentralized architecture is a challenging problem that arises in missions that require coordination among multiple vision-controlled robots. The depth estimation problem aims at recovering the 3D information of the environment. The relative localization problem consists of estimating the relative pose between two robots, by sensing each other's pose or sharing information about the perceived environment. Most solutions for these problems use a set of discrete data without taking into account the chronological order of the events. This paper builds on recent results on continuous estimation to propose a framework that estimates the depth and relative pose between two non-holonomic vehicles. The basic idea consists in estimating the depth of the points by explicitly considering the dynamics of the camera mounted on a ground robot, and feeding the estimates of 3D points observed by both cameras in a filter that computes the relative pose between the robots. We evaluate the convergence for a set of simulated scenarios and show experimental results validating the proposed framework.
Although significant improvement has been achieved recently in 3D human pose estimation, most of the previous methods only treat a single-person case. In this work, we firstly propose a fully learning-based, camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. The pipeline of the proposed system consists of human detection, absolute 3D human root localization, and root-relative 3D single-person pose estimation modules. Our system achieves comparable results with the state-of-the-art 3D single-person pose estimation models without any groundtruth information and significantly outperforms previous 3D multi-person pose estimation methods on publicly available datasets. The code is available in https://github.com/mks0601/3DMPPE_ROOTNET_RELEASE , https://github.com/mks0601/3DMPPE_POSENET_RELEASE.
We tackle the fundamentally ill-posed problem of 3D human localization from monocular RGB images. Driven by the limitation of neural networks outputting point estimates, we address the ambiguity in the task by predicting confidence intervals through a loss function based on the Laplace distribution. Our architecture is a light-weight feed-forward neural network that predicts 3D locations and corresponding confidence intervals given 2D human poses. The design is particularly well suited for small training data, cross-dataset generalization, and real-time applications. Our experiments show that we (i) outperform state-of-the-art results on KITTI and nuScenes datasets, (ii) even outperform a stereo-based method for far-away pedestrians, and (iii) estimate meaningful confidence intervals. We further share insights on our model of uncertainty in cases of limited observations and out-of-distribution samples.
Different layouts can characterize different aspects of the same graph. Finding a "good" layout of a graph is thus an important task for graph visualization. In practice, users often visualize a graph in multiple layouts by using different methods and varying parameter settings until they find a layout that best suits the purpose of the visualization. However, this trial-and-error process is often haphazard and time-consuming. To provide users with an intuitive way to navigate the layout design space, we present a technique to systematically visualize a graph in diverse layouts using deep generative models. We design an encoder-decoder architecture to learn a model from a collection of example layouts, where the encoder represents training examples in a latent space and the decoder produces layouts from the latent space. In particular, we train the model to construct a two-dimensional latent space for users to easily explore and generate various layouts. We demonstrate our approach through quantitative and qualitative evaluations of the generated layouts. The results of our evaluations show that our model is capable of learning and generalizing abstract concepts of graph layouts, not just memorizing the training examples. In summary, this paper presents a fundamentally new approach to graph visualization where a machine learning model learns to visualize a graph from examples without manually-defined heuristics.
Single-view depth estimation suffers from the problem that a network trained on images from one camera does not generalize to images taken with a different camera model. Thus, changing the camera model requires collecting an entirely new training dataset. In this work, we propose a new type of convolution that can take the camera parameters into account, thus allowing neural networks to learn calibration-aware patterns. Experiments confirm that this improves the generalization capabilities of depth prediction networks considerably, and clearly outperforms the state of the art when the train and test images are acquired with different cameras.
Modern day multimedia content generation and dissemination is moving towards the presentation of more and more `realistic' scenarios. The switch from 2-dimensional (2D) to 3-dimensional (3D) has been a major driving force in that direction. Over the recent past, a large number of approaches have been proposed for creating 3D images/videos most of which are based on the generation of depth-maps. This paper presents a new algorithm for obtaining depth information pertaining to a depicted scene from a set of available pair of stereoscopic images. The proposed algorithm performs a pixel-to-pixel matching of the two images in the stereo pair for estimation of depth. It is shown that the obtained depth-maps show improvements over the reported counterparts.
We present a method for turning a flash selfie taken with a smartphone into a photograph as if it was taken in a studio setting with uniform lighting. Our method uses a convolutional neural network trained on a set of pairs of photographs acquired in an ad-hoc acquisition campaign. Each pair consists of one photograph of a subject's face taken with the camera flash enabled and another one of the same subject in the same pose illuminated using a photographic studio-lighting setup. We show how our method can amend defects introduced by a close-up camera flash, such as specular highlights, shadows, skin shine, and flattened images.
This paper presents a new method for 3D depth estimation using the output of an asynchronous time driven image sensor. In association with a high speed Digital Light Processing projection system, our method achieves real-time reconstruction of 3D points cloud, up to several hundreds of hertz. Unlike state of the art methodology, we introduce a method that relies on the use of frequency tagged light pattern that make use of the high temporal resolution of event based sensors. This approch eases matching as each pattern unique frequency allow for any easy matching between displayed patterns and the event based sensor. Results are show on real scenes.
Many phenomena taking place in the solar photosphere are controlled by plasma motions. Although the line-of-sight component of the velocity can be estimated using the Doppler effect, we do not have direct spectroscopic access to the components that are perpendicular to the line-of-sight. These components are typically estimated using methods based on local correlation tracking. We have designed DeepVel, an end-to-end deep neural network that produces an estimation of the velocity at every single pixel and at every time step and at three different heights in the atmosphere from just two consecutive continuum images. We confront DeepVel with local correlation tracking, pointing out that they give very similar results in the time- and spatially-averaged cases. We use the network to study the evolution in height of the horizontal velocity field in fragmenting granules, supporting the buoyancy-braking mechanism for the formation of integranular lanes in these granules. We also show that DeepVel can capture very small vortices, so that we can potentially expand the scaling cascade of vortices to very small sizes and durations.