Novel view synthesis using neural radiance fields (NeRF) is the state-of-the-art technique for generating high-quality images from novel viewpoints. Existing methods require a priori knowledge about extrinsic and intrinsic camera parameters. This limits their applicability to synthetic scenes, or real-world scenarios with the necessity of a preprocessing step. Current research on the joint optimization of camera parameters and NeRF focuses on refining noisy extrinsic camera parameters and often relies on the preprocessing of intrinsic camera parameters. Further approaches are limited to cover only one single camera intrinsic. To address these limitations, we propose a novel end-to-end trainable approach called NeRFtrinsic Four. We utilize Gaussian Fourier features to estimate extrinsic camera parameters and dynamically predict varying intrinsic camera parameters through the supervision of the projection error. Our approach outperforms existing joint optimization methods on LLFF and BLEFF. In addition to these existing datasets, we introduce a new dataset called iFF with varying intrinsic camera parameters. NeRFtrinsic Four is a step forward in joint optimization NeRF-based view synthesis and enables more realistic and flexible rendering in real-world scenarios with varying camera parameters.
相關內容
In this paper, we propose a differentiable WORLD synthesizer and demonstrate its use in end-to-end audio style transfer tasks such as (singing) voice conversion and the DDSP timbre transfer task. Accordingly, our baseline differentiable synthesizer has no model parameters, yet it yields adequate synthesis quality. We can extend the baseline synthesizer by appending lightweight black-box postnets which apply further processing to the baseline output in order to improve fidelity. An alternative differentiable approach considers extraction of the source excitation spectrum directly, which can improve naturalness albeit for a narrower class of style transfer applications. The acoustic feature parameterization used by our approaches has the added benefit that it naturally disentangles pitch and timbral information so that they can be modeled separately. Moreover, as there exists a robust means of estimating these acoustic features from monophonic audio sources, it allows for parameter loss terms to be added to an end-to-end objective function, which can help convergence and/or further stabilize (adversarial) training.
One of the major challenges in multi-person pose estimation is instance-aware keypoint estimation. Previous methods address this problem by leveraging an off-the-shelf detector, heuristic post-grouping process or explicit instance identification process, hindering further improvements in the inference speed which is an important factor for practical applications. From the statistical point of view, those additional processes for identifying instances are necessary to bypass learning the high-dimensional joint distribution of human keypoints, which is a critical factor for another major challenge, the occlusion scenario. In this work, we propose a novel framework of single-stage instance-aware pose estimation by modeling the joint distribution of human keypoints with a mixture density model, termed as MDPose. Our MDPose estimates the distribution of human keypoints' coordinates using a mixture density model with an instance-aware keypoint head consisting simply of 8 convolutional layers. It is trained by minimizing the negative log-likelihood of the ground truth keypoints. Also, we propose a simple yet effective training strategy, Random Keypoint Grouping (RKG), which significantly alleviates the underflow problem leading to successful learning of relations between keypoints. On OCHuman dataset, which consists of images with highly occluded people, our MDPose achieves state-of-the-art performance by successfully learning the high-dimensional joint distribution of human keypoints. Furthermore, our MDPose shows significant improvement in inference speed with a competitive accuracy on MS COCO, a widely-used human keypoint dataset, thanks to the proposed much simpler single-stage pipeline.
Neural Radiance Fields has become a prominent method of scene generation via view synthesis. A critical requirement for the original algorithm to learn meaningful scene representation is camera pose information for each image in a data set. Current approaches try to circumnavigate this assumption with moderate success, by learning approximate camera positions alongside learning neural representations of a scene. This requires complicated camera models, causing a long and complicated training process, or results in a lack of texture and sharp details in rendered scenes. In this work we introduce Hash Color Correction (HashCC) -- a lightweight method for improving Neural Radiance Fields rendered image quality, applicable also in situations where camera positions for a given set of images are unknown.
Calibrating the extrinsic parameters of sensory devices is crucial for fusing multi-modal data. Recently, event cameras have emerged as a promising type of neuromorphic sensors, with many potential applications in fields such as mobile robotics and autonomous driving. When combined with LiDAR, they can provide more comprehensive information about the surrounding environment. Nonetheless, due to the distinctive representation of event cameras compared to traditional frame-based cameras, calibrating them with LiDAR presents a significant challenge. In this paper, we propose a novel method to calibrate the extrinsic parameters between a dyad of an event camera and a LiDAR without the need for a calibration board or other equipment. Our approach takes advantage of the fact that when an event camera is in motion, changes in reflectivity and geometric edges in the environment trigger numerous events, which can also be captured by LiDAR. Our proposed method leverages the edges extracted from events and point clouds and correlates them to estimate extrinsic parameters. Experimental results demonstrate that our proposed method is highly robust and effective in various scenes.
Feature Descriptors and Detectors are two main components of feature-based point cloud registration. However, little attention has been drawn to the explicit representation of local and global semantics in the learning of descriptors and detectors. In this paper, we present a framework that explicitly extracts dual-level descriptors and detectors and performs coarse-to-fine matching with them. First, to explicitly learn local and global semantics, we propose a hierarchical contrastive learning strategy, training the robust matching ability of high-level descriptors, and refining the local feature space using low-level descriptors. Furthermore, we propose to learn dual-level saliency maps that extract two groups of keypoints in two different senses. To overcome the weak supervision of binary matchability labels, we propose a ranking strategy to label the significance ranking of keypoints, and thus provide more fine-grained supervision signals. Finally, we propose a global-to-local matching scheme to obtain robust and accurate correspondences by leveraging the complementary dual-level features.Quantitative experiments on 3DMatch and KITTI odometry datasets show that our method achieves robust and accurate point cloud registration and outperforms recent keypoint-based methods.
We present a neural network-based simulation super-resolution framework that can efficiently and realistically enhance a facial performance produced by a low-cost, realtime physics-based simulation to a level of detail that closely approximates that of a reference-quality off-line simulator with much higher resolution (26x element count in our examples) and accurate physical modeling. Our approach is rooted in our ability to construct - via simulation - a training set of paired frames, from the low- and high-resolution simulators respectively, that are in semantic correspondence with each other. We use face animation as an exemplar of such a simulation domain, where creating this semantic congruence is achieved by simply dialing in the same muscle actuation controls and skeletal pose in the two simulators. Our proposed neural network super-resolution framework generalizes from this training set to unseen expressions, compensates for modeling discrepancies between the two simulations due to limited resolution or cost-cutting approximations in the real-time variant, and does not require any semantic descriptors or parameters to be provided as input, other than the result of the real-time simulation. We evaluate the efficacy of our pipeline on a variety of expressive performances and provide comparisons and ablation experiments for plausible variations and alternatives to our proposed scheme.
Contrastive loss has been increasingly used in learning representations from multiple modalities. In the limit, the nature of the contrastive loss encourages modalities to exactly match each other in the latent space. Yet it remains an open question how the modality alignment affects the downstream task performance. In this paper, based on an information-theoretic argument, we first prove that exact modality alignment is sub-optimal in general for downstream prediction tasks. Hence we advocate that the key of better performance lies in meaningful latent modality structures instead of perfect modality alignment. To this end, we propose three general approaches to construct latent modality structures. Specifically, we design 1) a deep feature separation loss for intra-modality regularization; 2) a Brownian-bridge loss for inter-modality regularization; and 3) a geometric consistency loss for both intra- and inter-modality regularization. Extensive experiments are conducted on two popular multi-modal representation learning frameworks: the CLIP-based two-tower model and the ALBEF-based fusion model. We test our model on a variety of tasks including zero/few-shot image classification, image-text retrieval, visual question answering, visual reasoning, and visual entailment. Our method achieves consistent improvements over existing methods, demonstrating the effectiveness and generalizability of our proposed approach on latent modality structure regularization.
Despite the recent progress in deep learning, most approaches still go for a silo-like solution, focusing on learning each task in isolation: training a separate neural network for each individual task. Many real-world problems, however, call for a multi-modal approach and, therefore, for multi-tasking models. Multi-task learning (MTL) aims to leverage useful information across tasks to improve the generalization capability of a model. This thesis is concerned with multi-task learning in the context of computer vision. First, we review existing approaches for MTL. Next, we propose several methods that tackle important aspects of multi-task learning. The proposed methods are evaluated on various benchmarks. The results show several advances in the state-of-the-art of multi-task learning. Finally, we discuss several possibilities for future work.
Convolutional neural networks (CNNs) have shown dramatic improvements in single image super-resolution (SISR) by using large-scale external samples. Despite their remarkable performance based on the external dataset, they cannot exploit internal information within a specific image. Another problem is that they are applicable only to the specific condition of data that they are supervised. For instance, the low-resolution (LR) image should be a "bicubic" downsampled noise-free image from a high-resolution (HR) one. To address both issues, zero-shot super-resolution (ZSSR) has been proposed for flexible internal learning. However, they require thousands of gradient updates, i.e., long inference time. In this paper, we present Meta-Transfer Learning for Zero-Shot Super-Resolution (MZSR), which leverages ZSSR. Precisely, it is based on finding a generic initial parameter that is suitable for internal learning. Thus, we can exploit both external and internal information, where one single gradient update can yield quite considerable results. (See Figure 1). With our method, the network can quickly adapt to a given image condition. In this respect, our method can be applied to a large spectrum of image conditions within a fast adaptation process.
We propose a new method for event extraction (EE) task based on an imitation learning framework, specifically, inverse reinforcement learning (IRL) via generative adversarial network (GAN). The GAN estimates proper rewards according to the difference between the actions committed by the expert (or ground truth) and the agent among complicated states in the environment. EE task benefits from these dynamic rewards because instances and labels yield to various extents of difficulty and the gains are expected to be diverse -- e.g., an ambiguous but correctly detected trigger or argument should receive high gains -- while the traditional RL models usually neglect such differences and pay equal attention on all instances. Moreover, our experiments also demonstrate that the proposed framework outperforms state-of-the-art methods, without explicit feature engineering.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191