PyTorchKR Papers

최신 논문

총 846편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

arXiv:2305.01611공식 코드 · Papers with Code

AutoColor: Learned Light Power Control for Multi-Color Holograms

Multi-color holograms rely on simultaneous illumination from multiple light sources. These multi-color holograms could utilize light sources better than conventional single-color holograms and can improve the dynamic range of holographic displays. In this letter, we introduce AutoColor , the first learned method for estimating the optimal light source powers required for illuminating multi-color holograms. For this purpose, we establish the first multi-color hologram dataset using synthetic images and their depth information. We generate these synthetic images using a trending pipeline combining generative, large language, and monocular depth estimation models. Finally, we train our learned model using our dataset and experimentally demonstrate that AutoColor significantly decreases the number of steps required to optimize multi-color holograms from > 1000 to 70 iteration steps without compromising image quality.

arXiv:2305.00041공식 코드 · Papers with Code

ViP-NeRF: Visibility Prior for Sparse Input Neural Radiance Fields

Neural radiance fields (NeRF) have achieved impressive performances in view synthesis by encoding neural representations of a scene. However, NeRFs require hundreds of images per scene to synthesize photo-realistic novel views. Training them on sparse input views leads to overfitting and incorrect scene depth estimation resulting in artifacts in the rendered novel views. Sparse input NeRFs were recently regularized by providing dense depth estimated from pre-trained networks as supervision, to achieve improved performance over sparse depth constraints. However, we find that such depth priors may be inaccurate due to generalization issues. Instead, we hypothesize that the visibility of pixels in different input views can be more reliably estimated to provide dense supervision. In this regard, we compute a visibility prior through the use of plane sweep volumes, which does not require any pre-training. By regularizing the NeRF training with the visibility prior, we successfully train the NeRF with few input views. We reformulate the NeRF to also directly output the visibility of a 3D point from a given viewpoint to reduce the training time with the visibility constraint. On multiple datasets, our model outperforms the competing sparse input NeRF models including those that use learned priors. The source code for our model can be found on our project page: https://nagabhushansn95.github.io/publications/2023/ViP-NeRF.html.

arXiv:2304.13030공식 코드 · Papers with Code

CompletionFormer: Depth Completion with Convolutions and Vision Transformers

Given sparse depths and the corresponding RGB images, depth completion aims at spatially propagating the sparse measurements throughout the whole image to get a dense depth prediction. Despite the tremendous progress of deep-learning-based depth completion methods, the locality of the convolutional layer or graph model makes it hard for the network to model the long-range relationship between pixels. While recent fully Transformer-based architecture has reported encouraging results with the global receptive field, the performance and efficiency gaps to the well-developed CNN models still exist because of its deteriorative local feature details. This paper proposes a Joint Convolutional Attention and Transformer block (JCAT), which deeply couples the convolutional attention layer and Vision Transformer into one block, as the basic unit to construct our depth completion model in a pyramidal structure. This hybrid architecture naturally benefits both the local connectivity of convolutions and the global context of the Transformer in one single model. As a result, our CompletionFormer outperforms state-of-the-art CNNs-based methods on the outdoor KITTI Depth Completion benchmark and indoor NYUv2 dataset, achieving significantly higher efficiency (nearly 1/3 FLOPs) compared to pure Transformer-based methods. Code is available at \url{https://github.com/youmi-zym/CompletionFormer}.

arXiv:2304.12685공식 코드 · Papers with Code

Exploring the Mutual Influence between Self-Supervised Single-Frame and Multi-Frame Depth Estimation

Although both self-supervised single-frame and multi-frame depth estimation methods only require unlabeled monocular videos for training, the information they leverage varies because single-frame methods mainly rely on appearance-based features while multi-frame methods focus on geometric cues. Considering the complementary information of single-frame and multi-frame methods, some works attempt to leverage single-frame depth to improve multi-frame depth. However, these methods can neither exploit the difference between single-frame depth and multi-frame depth to improve multi-frame depth nor leverage multi-frame depth to optimize single-frame depth models. To fully utilize the mutual influence between single-frame and multi-frame methods, we propose a novel self-supervised training framework. Specifically, we first introduce a pixel-wise adaptive depth sampling module guided by single-frame depth to train the multi-frame model. Then, we leverage the minimum reprojection based distillation loss to transfer the knowledge from the multi-frame depth network to the single-frame network to improve single-frame depth. Finally, we regard the improved single-frame depth as a prior to further boost the performance of multi-frame depth estimation. Experimental results on the KITTI and Cityscapes datasets show that our method outperforms existing approaches in the self-supervised monocular setting.

arXiv:2304.11677공식 코드 · Papers with Code

RGB-D Indiscernible Object Counting in Underwater Scenes

Recently, indiscernible/camouflaged scene understanding has attracted lots of research attention in the vision community. We further advance the frontier of this field by systematically studying a new challenge named indiscernible object counting (IOC), the goal of which is to count objects that are blended with respect to their surroundings. Due to a lack of appropriate IOC datasets, we present a large-scale dataset IOCfish5K which contains a total of 5,637 high-resolution images and 659,024 annotated center points. Our dataset consists of a large number of indiscernible objects (mainly fish) in underwater scenes, making the annotation process all the more challenging. IOCfish5K is superior to existing datasets with indiscernible scenes because of its larger scale, higher image resolutions, more annotations, and denser scenes. All these aspects make it the most challenging dataset for IOC so far, supporting progress in this area. Benefiting from the recent advancements of depth estimation foundation models, we construct high-quality depth maps for IOCfish5K by generating pseudo labels using the Depth Anything V2 model. The RGB-D version of IOCfish5K is named IOCfish5K-D. For benchmarking purposes on IOCfish5K, we select 14 mainstream methods for object counting and carefully evaluate them. For multimodal IOCfish5K-D, we evaluate other 4 popular multimodal counting methods. Furthermore, we propose IOCFormer, a new strong baseline that combines density and regression branches in a unified framework and can effectively tackle object counting under concealed scenes. We also propose IOCFormer-D to enable the effective usage of depth modality in helping detect and count objects hidden in their environments. Experiments show that IOCFormer and IOCFormer-D achieve state-of-the-art scores on IOCfish5K and IOCfish5K-D, respectively.

arXiv:2304.11161공식 코드 · Papers with Code

altiro3D: Scene representation from single image and novel view synthesis

We introduce altiro3D, a free extended library developed to represent reality starting from a given original RGB image or flat video. It allows to generate a light-field (or Native) image or video and get a realistic 3D experience. To synthesize N-number of virtual images and add them sequentially into a Quilt collage, we apply MiDaS models for the monocular depth estimation, simple OpenCV and Telea inpainting techniques to map all pixels, and implement a 'Fast' algorithm to handle 3D projection camera and scene transformations along N-viewpoints. We use the degree of depth to move proportionally the pixels, assuming the original image to be at the center of all the viewpoints. altiro3D can also be used with DIBR algorithm to compute intermediate snapshots from a equivalent 'Real (slower)' camera with N-geometric viewpoints, which requires to calibrate a priori several intrinsic and extrinsic camera parameters. We adopt a pixel- and device-based Lookup Table to optimize computing time. The multiple viewpoints and video generated from a single image or frame can be displayed in a free-view LCD display.

arXiv:2304.10241공식 코드 · Papers with Code

A geometry-aware deep network for depth estimation in monocular endoscopy

Monocular depth estimation is critical for endoscopists to perform spatial perception and 3D navigation of surgical sites. However, most of the existing methods ignore the important geometric structural consistency, which inevitably leads to performance degradation and distortion of 3D reconstruction. To address this issue, we introduce a gradient loss to penalize edge fluctuations ambiguous around stepped edge structures and a normal loss to explicitly express the sensitivity to frequently small structures, and propose a geometric consistency loss to spreads the spatial information across the sample grids to constrain the global geometric anatomy structures. In addition, we develop a synthetic RGB-Depth dataset that captures the anatomical structures under reflections and illumination variations. The proposed method is extensively validated across different datasets and clinical images and achieves mean RMSE values of 0.066 (stomach), 0.029 (small intestine), and 0.139 (colon) on the EndoSLAM dataset. The generalizability of the proposed method achieves mean RMSE values of 12.604 (T1-L1), 9.930 (T2-L2), and 13.893 (T3-L3) on the ColonDepth dataset. The experimental results show that our method exceeds previous state-of-the-art competitors and generates more consistent depth maps and reasonable anatomical structures. The quality of intraoperative 3D structure perception from endoscopic videos of the proposed method meets the accuracy requirements of video-CT registration algorithms for endoscopic navigation. The dataset and the source code will be available at https://github.com/YYM-SIA/LINGMI-MR.

arXiv:2304.08993공식 코드 · Papers with Code

Learning to Fuse Monocular and Multi-view Cues for Multi-frame Depth Estimation in Dynamic Scenes

Multi-frame depth estimation generally achieves high accuracy relying on the multi-view geometric consistency. When applied in dynamic scenes, e.g., autonomous driving, this consistency is usually violated in the dynamic areas, leading to corrupted estimations. Many multi-frame methods handle dynamic areas by identifying them with explicit masks and compensating the multi-view cues with monocular cues represented as local monocular depth or features. The improvements are limited due to the uncontrolled quality of the masks and the underutilized benefits of the fusion of the two types of cues. In this paper, we propose a novel method to learn to fuse the multi-view and monocular cues encoded as volumes without needing the heuristically crafted masks. As unveiled in our analyses, the multi-view cues capture more accurate geometric information in static areas, and the monocular cues capture more useful contexts in dynamic areas. To let the geometric perception learned from multi-view cues in static areas propagate to the monocular representation in dynamic areas and let monocular cues enhance the representation of multi-view cost volume, we propose a cross-cue fusion (CCF) module, which includes the cross-cue attention (CCA) to encode the spatially non-local relative intra-relations from each source to enhance the representation of the other. Experiments on real-world datasets prove the significant effectiveness and generalization ability of the proposed method.

arXiv:2304.08916공식 코드 · Papers with Code

Pose Constraints for Consistent Self-supervised Monocular Depth and Ego-motion

Self-supervised monocular depth estimation approaches suffer not only from scale ambiguity but also infer temporally inconsistent depth maps w.r.t. scale. While disambiguating scale during training is not possible without some kind of ground truth supervision, having scale consistent depth predictions would make it possible to calculate scale once during inference as a post-processing step and use it over-time. With this as a goal, a set of temporal consistency losses that minimize pose inconsistencies over time are introduced. Evaluations show that introducing these constraints not only reduces depth inconsistencies but also improves the baseline performance of depth and ego-motion prediction.

arXiv:2304.07435공식 코드 · Papers with Code

Temporally Consistent Online Depth Estimation Using Point-Based Fusion

Depth estimation is an important step in many computer vision problems such as 3D reconstruction, novel view synthesis, and computational photography. Most existing work focuses on depth estimation from single frames. When applied to videos, the result lacks temporal consistency, showing flickering and swimming artifacts. In this paper we aim to estimate temporally consistent depth maps of video streams in an online setting. This is a difficult problem as future frames are not available and the method must choose between enforcing consistency and correcting errors from previous estimations. The presence of dynamic objects further complicates the problem. We propose to address these challenges by using a global point cloud that is dynamically updated each frame, along with a learned fusion approach in image space. Our approach encourages consistency while simultaneously allowing updates to handle errors and dynamic objects. Qualitative and quantitative results show that our method achieves state-of-the-art quality for consistent video depth estimation.

arXiv:2304.07193공식 코드 · Papers with Code

DINOv2: Learning Robust Visual Features without Supervision

The recent breakthroughs in natural language processing for model pretraining on large quantities of data have opened the way for similar foundation models in computer vision. These models could greatly simplify the use of images in any system by producing all-purpose visual features, i.e., features that work across image distributions and tasks without finetuning. This work shows that existing pretraining methods, especially self-supervised methods, can produce such features if trained on enough curated data from diverse sources. We revisit existing approaches and combine different techniques to scale our pretraining in terms of data and model size. Most of the technical contributions aim at accelerating and stabilizing the training at scale. In terms of data, we propose an automatic pipeline to build a dedicated, diverse, and curated image dataset instead of uncurated data, as typically done in the self-supervised literature. In terms of models, we train a ViT model (Dosovitskiy et al., 2020) with 1B parameters and distill it into a series of smaller models that surpass the best available all-purpose features, OpenCLIP (Ilharco et al., 2021) on most of the benchmarks at image and pixel levels.

arXiv:2304.06966공식 코드 · Papers with Code

Self-Supervised Learning based Depth Estimation from Monocular Images

Depth Estimation has wide reaching applications in the field of Computer vision such as target tracking, augmented reality, and self-driving cars. The goal of Monocular Depth Estimation is to predict the depth map, given a 2D monocular RGB image as input. The traditional depth estimation methods are based on depth cues and used concepts like epipolar geometry. With the evolution of Convolutional Neural Networks, depth estimation has undergone tremendous strides. In this project, our aim is to explore possible extensions to existing SoTA Deep Learning based Depth Estimation Models and to see whether performance metrics could be further improved. In a broader sense, we are looking at the possibility of implementing Pose Estimation, Efficient Sub-Pixel Convolution Interpolation, Semantic Segmentation Estimation techniques to further enhance our proposed architecture and to provide fine-grained and more globally coherent depth map predictions. We also plan to do away with camera intrinsic parameters during training and apply weather augmentations to further generalize our model.

arXiv:2304.06334공식 코드 · Papers with Code

iDisc: Internal Discretization for Monocular Depth Estimation

Monocular depth estimation is fundamental for 3D scene understanding and downstream applications. However, even under the supervised setup, it is still challenging and ill-posed due to the lack of full geometric constraints. Although a scene can consist of millions of pixels, there are fewer high-level patterns. We propose iDisc to learn those patterns with internal discretized representations. The method implicitly partitions the scene into a set of high-level patterns. In particular, our new module, Internal Discretization (ID), implements a continuous-discrete-continuous bottleneck to learn those concepts without supervision. In contrast to state-of-the-art methods, the proposed model does not enforce any explicit constraints or priors on the depth output. The whole network with the ID module can be trained end-to-end, thanks to the bottleneck module based on attention. Our method sets the new state of the art with significant improvements on NYU-Depth v2 and KITTI, outperforming all published methods on the official KITTI benchmark. iDisc can also achieve state-of-the-art results on surface normal estimation. Further, we explore the model generalization capability via zero-shot testing. We observe the compelling need to promote diversification in the outdoor scenario. Hence, we introduce splits of two autonomous driving datasets, DDAD and Argoverse. Code is available at http://vis.xyz/pub/idisc .

arXiv:2304.05218공식 코드 · Papers with Code

Improving Neural Radiance Fields with Depth-aware Optimization for Novel View Synthesis

With dense inputs, Neural Radiance Fields (NeRF) is able to render photo-realistic novel views under static conditions. Although the synthesis quality is excellent, existing NeRF-based methods fail to obtain moderate three-dimensional (3D) structures. The novel view synthesis quality drops dramatically given sparse input due to the implicitly reconstructed inaccurate 3D-scene structure. We propose SfMNeRF, a method to better synthesize novel views as well as reconstruct the 3D-scene geometry. SfMNeRF leverages the knowledge from the self-supervised depth estimation methods to constrain the 3D-scene geometry during view synthesis training. Specifically, SfMNeRF employs the epipolar, photometric consistency, depth smoothness, and position-of-matches constraints to explicitly reconstruct the 3D-scene structure. Through these explicit constraints and the implicit constraint from NeRF, our method improves the view synthesis as well as the 3D-scene geometry performance of NeRF at the same time. In addition, SfMNeRF synthesizes novel sub-pixels in which the ground truth is obtained by image interpolation. This strategy enables SfMNeRF to include more samples to improve generalization performance. Experiments on two public datasets demonstrate that SfMNeRF surpasses state-of-the-art approaches. Code is available at https://github.com/XTU-PR-LAB/SfMNeRF

arXiv:2304.03560공식 코드 · Papers with Code

DualRefine: Self-Supervised Depth and Pose Estimation Through Iterative Epipolar Sampling and Refinement Toward Equilibrium

Self-supervised multi-frame depth estimation achieves high accuracy by computing matching costs of pixel correspondences between adjacent frames, injecting geometric information into the network. These pixel-correspondence candidates are computed based on the relative pose estimates between the frames. Accurate pose predictions are essential for precise matching cost computation as they influence the epipolar geometry. Furthermore, improved depth estimates can, in turn, be used to align pose estimates. Inspired by traditional structure-from-motion (SfM) principles, we propose the DualRefine model, which tightly couples depth and pose estimation through a feedback loop. Our novel update pipeline uses a deep equilibrium model framework to iteratively refine depth estimates and a hidden state of feature maps by computing local matching costs based on epipolar geometry. Importantly, we used the refined depth estimates and feature maps to compute pose updates at each step. This update in the pose estimates slowly alters the epipolar geometry during the refinement process. Experimental results on the KITTI dataset demonstrate competitive depth prediction and odometry prediction performance surpassing published self-supervised baselines.

arXiv:2304.02569공식 코드 · Papers with Code

DEFLOW: Self-supervised 3D Motion Estimation of Debris Flow

Existing work on scene flow estimation focuses on autonomous driving and mobile robotics, while automated solutions are lacking for motion in nature, such as that exhibited by debris flows. We propose DEFLOW, a model for 3D motion estimation of debris flows, together with a newly captured dataset. We adopt a novel multi-level sensor fusion architecture and self-supervision to incorporate the inductive biases of the scene. We further adopt a multi-frame temporal processing module to enable flow speed estimation over time. Our model achieves state-of-the-art optical flow and depth estimation on our dataset, and fully automates the motion estimation for debris flows. The source code and dataset are available at project page.

arXiv:2304.00971공식 코드 · Papers with Code

Joint 2D-3D Multi-Task Learning on Cityscapes-3D: 3D Detection, Segmentation, and Depth Estimation

This report serves as a supplementary document for TaskPrompter, detailing its implementation on a new joint 2D-3D multi-task learning benchmark based on Cityscapes-3D. TaskPrompter presents an innovative multi-task prompting framework that unifies the learning of (i) task-generic representations, (ii) task-specific representations, and (iii) cross-task interactions, as opposed to previous approaches that separate these learning objectives into different network modules. This unified approach not only reduces the need for meticulous empirical structure design but also significantly enhances the multi-task network's representation learning capability, as the entire model capacity is devoted to optimizing the three objectives simultaneously. TaskPrompter introduces a new multi-task benchmark based on Cityscapes-3D dataset, which requires the multi-task model to concurrently generate predictions for monocular 3D vehicle detection, semantic segmentation, and monocular depth estimation. These tasks are essential for achieving a joint 2D-3D understanding of visual scenes, particularly in the development of autonomous driving systems. On this challenging benchmark, our multi-task model demonstrates strong performance compared to single-task state-of-the-art methods and establishes new state-of-the-art results on the challenging 3D detection and depth estimation tasks.

arXiv:2303.17895공식 코드 · Papers with Code

EA-LSS: Edge-aware Lift-splat-shot Framework for 3D BEV Object Detection

In recent years, great progress has been made in the Lift-Splat-Shot-based (LSS-based) 3D object detection method. However, inaccurate depth estimation remains an important constraint to the accuracy of camera-only and multi-model 3D object detection models, especially in regions where the depth changes significantly (i.e., the "depth jump" problem). In this paper, we proposed a novel Edge-aware Lift-splat-shot (EA-LSS) framework. Specifically, edge-aware depth fusion (EADF) module is proposed to alleviate the "depth jump" problem and fine-grained depth (FGD) module to further enforce refined supervision on depth. Our EA-LSS framework is compatible for any LSS-based 3D object detection models, and effectively boosts their performances with negligible increment of inference time. Experiments on nuScenes benchmarks demonstrate that EA-LSS is effective in either camera-only or multi-model models. It is worth mentioning that EA-LSS achieved the state-of-the-art performance on nuScenes test benchmarks with mAP and NDS of 76.5% and 77.6%, respectively.

arXiv:2303.17766공식 코드 · Papers with Code

Joint Depth Estimation and Mixture of Rain Removal From a Single Image

Rainy weather significantly deteriorates the visibility of scene objects, particularly when images are captured through outdoor camera lenses or windshields. Through careful observation of numerous rainy photos, we have found that the images are generally affected by various rainwater artifacts such as raindrops, rain streaks, and rainy haze, which impact the image quality from both near and far distances, resulting in a complex and intertwined process of image degradation. However, current deraining techniques are limited in their ability to address only one or two types of rainwater, which poses a challenge in removing the mixture of rain (MOR). In this study, we propose an effective image deraining paradigm for Mixture of rain REmoval, called DEMore-Net, which takes full account of the MOR effect. Going beyond the existing deraining wisdom, DEMore-Net is a joint learning paradigm that integrates depth estimation and MOR removal tasks to achieve superior rain removal. The depth information can offer additional meaningful guidance information based on distance, thus better helping DEMore-Net remove different types of rainwater. Moreover, this study explores normalization approaches in image deraining tasks and introduces a new Hybrid Normalization Block (HNB) to enhance the deraining performance of DEMore-Net. Extensive experiments conducted on synthetic datasets and real-world MOR photos fully validate the superiority of the proposed DEMore-Net. Code is available at https://github.com/yz-wang/DEMore-Net.

arXiv:2303.17559공식 코드 · Papers with Code

DDP: Diffusion Model for Dense Visual Prediction

We propose a simple, efficient, yet powerful framework for dense visual predictions based on the conditional diffusion pipeline. Our approach follows a "noise-to-map" generative paradigm for prediction by progressively removing noise from a random Gaussian distribution, guided by the image. The method, called DDP, efficiently extends the denoising diffusion process into the modern perception pipeline. Without task-specific design and architecture customization, DDP is easy to generalize to most dense prediction tasks, e.g., semantic segmentation and depth estimation. In addition, DDP shows attractive properties such as dynamic inference and uncertainty awareness, in contrast to previous single-step discriminative methods. We show top results on three representative tasks with six diverse benchmarks, without tricks, DDP achieves state-of-the-art or competitive performance on each task compared to the specialist counterparts. For example, semantic segmentation (83.9 mIoU on Cityscapes), BEV map segmentation (70.6 mIoU on nuScenes), and depth estimation (0.05 REL on KITTI). We hope that our approach will serve as a solid baseline and facilitate future research