We present a learning-based method for interpolating and manipulating 3D shapes represented as point clouds, that is explicitly designed to preserve intrinsic shape properties. Our approach is based on constructing a dual encoding space that enables shape synthesis and, at the same time, provides links to the intrinsic shape information, which is typically not available on point cloud data. Our method works in a single pass and avoids expensive optimization, employed by existing techniques. Furthermore, the strong regularization provided by our dual latent space approach also helps to improve shape recovery in challenging settings from noisy point clouds across different datasets. Extensive experiments show that our method results in more realistic and smoother interpolations compared to baselines.
NaviNeRF: NeRF-based 3D Representation Disentanglement by Latent Semantic Navigation
Tianjin University（天津大学）；Eastern Institute of Technology（东方理工学院）；Ningbo Institute of Digital Twin（宁波数字孪生研究院）；Shanghai Jiao Tong University（上海交通大学）；Northwest Normal University（西北师范大学）；Zhejiang University（浙江大学）
CNRS (LIX), IP Paris, École Polytechnique（法国国家科学研究中心(LIX)，巴黎理工学院，巴黎综合理工学院）；Caritas Institute of Higher Education（明爱专上学院）；The Hong Kong Polytechnic University（香港理工大学）
Institute of Information Science, Beijing Jiaotong University（北京交通大学信息科学研究所）；College of Electronic Science and Technology, National University of Defense Technology（国防科技大学电子科学学院）
LiDAR sensors can provide dependable 3D spatial information at a low frequency (around 10Hz) and have been widely applied in the field of autonomous driving and UAV. However, the camera with a higher frequency (around 20Hz) has to be decreased so as to match with LiDAR in a multi-sensor system. In this paper, we propose a novel Pseudo-LiDAR interpolation network (PLIN) to increase the frequency of LiDAR sensors. PLIN can generate temporally and spatially high-quality point cloud sequences to match the high frequency of cameras. To achieve this goal, we design a coarse interpolation stage guide…
Due to the remarkable progress of deep generative models, animating images has become increasingly efficient, whereas associated results have become increasingly realistic. Current animation-approaches commonly exploit structure representation extracted from driving videos. Such structure representation is instrumental in transferring motion from driving videos to still images. However, such approaches fail in case the source image and driving video encompass large appearance variation. Moreover, the extraction of structure information requires additional modules that endow the animation-model…
Prediction and interpolation for long-range video data involves the complex task of modeling motion trajectories for each visible object, occlusions and dis-occlusions, as well as appearance changes due to viewpoint and lighting. Optical flow based techniques generalize but are suitable only for short temporal ranges. Many methods opt to project the video frames to a low dimensional latent space, achieving long-range predictions. However, these latent representations are often non-interpretable, and therefore difficult to manipulate. This work poses video prediction and interpolation as unsupe…
Existing works address the problem of generating high frame-rate sharp videos by separately learning the frame deblurring and frame interpolation modules. Most of these approaches have a strong prior assumption that all the input frames are blurry whereas in a real-world setting, the quality of frames varies. Moreover, such approaches are trained to perform either of the two tasks - deblurring or interpolation - in isolation, while many practical situations call for both. Different from these works, we address a more realistic problem of high frame-rate sharp video synthesis with no prior assu…
Bernoulli Institute, University of Groningen（格罗宁根大学伯努利研究所）
The task of text-to-image generation has achieved remarkable progress due to the advances in the conditional generative adversarial networks (GANs). However, existing conditional text-to-image GANs approaches mostly concentrate on improving both image quality and semantic relevance but ignore the explainability of the model which plays a vital role in real-world applications. In this paper, we present a variety of techniques to take a deep look into the latent space and semantic space of the conditional text-to-image GANs model. We introduce pairwise linear interpolation of latent codes and `l…
PROSPECT: Unified Streaming Vision-Language Navigation via Semantic--Spatial Fusion and Latent Predictive Representation
Shanghai Jiao Tong University（上海交通大学）；Tsinghua University（清华大学）；University of Adelaide（阿德莱德大学）；Wuhan University（武汉大学）；Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Beijing Jiaotong University（北京交通大学）；AIR Wuxi Innovation Center, Tsinghua University（清华大学无锡创新中心）；Lenovo（联想集团）
Video Latent Flow Matching: Optimal Polynomial Projections for Video Interpolation and Extrapolation
Wyoming Seminary（怀俄明神学院）；Simons Institute for the Theory of Computing, University of California, Berkeley（加州大学伯克利分校西蒙斯理论计算研究所）；Sun Yat-sen University（中山大学）
本文提出 Video Latent Flow Matching (VLFM)，利用预训练图像生成模型和 HiPPO 最优多项式投影建模潜在块流，实现任意帧率的视频插值与外推生成，并具备理论逼近误差和时间尺度鲁棒性优势。
University of Trento（特伦托大学）；Tencent AI Lab（腾讯人工智能实验室）；Fondazione Bruno Kessler（布鲁诺·凯塞勒基金会）
Image-to-Image (I2I) multi-domain translation models are usually evaluated also using the quality of their semantic interpolation results. However, state-of-the-art models frequently show abrupt changes in the image appearance during interpolation, and usually perform poorly in interpolations across domains. In this paper, we propose a new training protocol based on three specific losses which help a translation network to learn a smooth and disentangled latent style space in which: 1) Both intra- and inter-domain interpolations correspond to gradual changes in the generated images and 2) The …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
Controllable semantic image editing enables a user to change entire image attributes with a few clicks, e.g., gradually making a summer scene look like it was taken in winter. Classic approaches for this task use a Generative Adversarial Net (GAN) to learn a latent space and suitable latent-space transformations. However, current approaches often suffer from attribute edits that are entangled, global image identity changes, and diminished photo-realism. To address these concerns, we learn multiple attribute transformations simultaneously, integrate attribute regression into the training of tra…
LatentPilot: Scene-Aware Vision-and-Language Navigation by Dreaming Ahead with Latent Visual Reasoning
University of Science and Technology of China（中国科学技术大学）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；Stanford University（斯坦福大学）；Amap, Alibaba Group（阿里巴巴集团高德地图）；Shanghai AI Laboratory（上海人工智能实验室）
This paper will discuss the potential of dimensionality reduction with a web-based use of GANs. Throughout a variety of experiments, we show synthesizing visually-appealing samples, interpolating meaningfully between samples, and performing linear arithmetic with latent vectors. GANs have proved to be a remarkable technique to produce computer-generated images, very similar to an original image. This is primarily useful when coupled with dimensionality reduction as an effective application of our algorithm. We proposed a new architecture for GANs, which ended up not working for mathematical re…
Generative neural networks have a well recognized ability to estimate underlying manifold structure of high dimensional data. However, if a single latent space is used, it is not possible to faithfully represent a manifold with topology different from Euclidean space. In this work we define the general class of Atlas Generative Models (AGMs), models with hybrid discrete-continuous latent space that estimate an atlas on the underlying data manifold together with a partition of unity on the data space. We identify existing examples of models from various popular generative paradigms that fit int…
HuTuMotion: Human-Tuned Navigation of Latent Motion Diffusion Models with Minimal Feedback
Northwest A&F University（西北农林科技大学）；Tencent AI Lab（腾讯AI实验室）；The University of Melbourne（墨尔本大学）；Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）
University of Trento（特伦托大学）；Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；Shanghai Jiao Tong University（上海交通大学）；Tencent AI Lab（腾讯人工智能实验室）
Multi-domain image-to-image (I2I) translations can transform a source image according to the style of a target domain. One important, desired characteristic of these transformations, is their graduality, which corresponds to a smooth change between the source and the target image when their respective latent-space representations are linearly interpolated. However, state-of-the-art methods usually perform poorly when evaluated using inter-domain interpolations, often producing abrupt changes in the appearance or non-realistic intermediate images. In this paper, we argue that one of the main re…
Department of Computing, Goldsmiths University of London（伦敦大学金史密斯学院计算机系）；Creative Computing Institute, University of the Arts, London（伦敦艺术大学创意计算学院）
We introduce a method which allows users to creatively explore and navigate the vast latent spaces of deep generative models. Specifically, our method enables users to \textit{discover} and \textit{design} \textit{trajectories} in these high dimensional spaces, to construct stories, and produce time-based media such as videos---\textit{with meaningful control over narrative}. Our goal is to encourage and aid the use of deep generative models as a medium for creative expression and story telling with meaningful human control. Our method is analogous to traditional video production pipelines in …
We focus on controllable disentangled representation learning (C-Dis-RL), where users can control the partition of the disentangled latent space to factorize dataset attributes (concepts) for downstream tasks. Two general problems remain under-explored in current methods: (1) They lack comprehensive disentanglement constraints, especially missing the minimization of mutual information between different attributes across latent and observation domains. (2) They lack convexity constraints, which is important for meaningfully manipulating specific attributes for downstream tasks. To encourage bot…
Auto encoding models have been extensively studied in recent years. They provide an efficient framework for sample generation, as well as for analysing feature learning. Furthermore, they are efficient in performing interpolations between data-points in semantically meaningful ways. In this paper, we build further on a previously introduced method for generating canonical, dimension independent, stochastic interpolations. Here, the distribution of interpolation paths is represented as the distribution of a bridge process constructed from an artificial random data generating process in the late…
GeoScaffold: Learning Compact Geometric Latents via Reconstruction for Efficient Vision-Language Navigation
Nanjing University（南京大学）；Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；MAICRO（迈克罗）
VTAE: Variational Transformer Autoencoder with Manifolds Learning
East China Normal University（华东师范大学）；Shanghai Jiao Tong University（上海交通大学）；University of Leicester（莱斯特大学）；The University of Sydney（悉尼大学）；Northwestern Polytechnical University（西北工业大学）
Agents navigating in 3D environments require some form of memory, which should hold a compact and actionable representation of the history of observations useful for decision taking and planning. In most end-to-end learning approaches the representation is latent and usually does not have a clearly defined interpretation, whereas classical robotics addresses this with scene reconstruction resulting in some form of map, usually estimated with geometry and sensor models and/or learning. In this work we propose to learn an actionable representation of the scene independently of the targeted downs…
We propose a generative framework which takes on the video frame interpolation problem. Our framework, which we call Deep Locally Linear Embedding (DeepLLE), is powered by a deep convolutional neural network (CNN) while it can be used instantly like conventional models. DeepLLE fits an auto-encoding CNN to a set of several consecutive frames and embeds a linearity constraint on the latent codes so that new frames can be generated by interpolating new latent codes. Different from the current deep learning paradigm which requires training on large datasets, DeepLLE works in a plug-and-play and u…
The Australian Institute for Machine Learning（澳大利亚机器学习研究所）；The University of Adelaide（阿德莱德大学）
Visual navigation is often cast as a reinforcement learning (RL) problem. Current methods typically result in a suboptimal policy that learns general obstacle avoidance and search behaviours. For example, in the target-object navigation setting, the policies learnt by traditional methods often fail to complete the task, even when the target is clearly within reach from a human perspective. In order to address this issue, we propose to learn to imagine a latent representation of the successful (sub-)goal state. To do so, we have developed a module which we call Foresight Imagination (ForeSIT). …
Latent Interpolation Learning Using Diffusion Models for Cardiac Volume Reconstruction
School of Computation, Information and Technology, Technical University Munich（技术大学慕尼黑计算信息学院）；Munich Center for Machine Learning（慕尼黑机器学习中心）；Department of Quantitative Biomedicine, University of Zurich（苏黎世大学定量生物医学系）；Institute of Biomedical Engineering, Department of Engineering Science, University of Oxford（牛津大学生物医学工程研究所）；Imperial College London（伦敦帝国学院）；University of Sheffield（谢菲尔德大学）；NVIDIA（英伟达）；Department of Computing, Imperial College London（伦敦帝国学院计算机系）；Department AIBE of Friedrich-Alexander-Universität Erlangen-Nürnberg（埃尔兰根-纽伦堡大学AIBE系）；School of Medicine, Klinikum Rechts der Isar, Technical University of Munich（慕尼黑技术大学医学院，莱纳特医院）
Indian Institute of Technology Kanpur（印度理工学院坎普尔分校）
A wide range of applications require learning image generation models whose latent space effectively captures the high-level factors of variation present in the data distribution. The extent to which a model represents such variations through its latent space can be judged by its ability to interpolate between images smoothly. However, most generative models mapping a fixed prior to the generated images lead to interpolation trajectories lacking smoothness and containing images of reduced quality. In this work, we propose a novel generative model that learns a flexible non-parametric prior ove…
Gatsby Computational Neuroscience Unit, University College London（伦敦大学学院盖茨比计算神经科学单元）；Department of Mathematics and Center for Scientific Computation and Mathematical Modeling, University of Maryland College Park（马里兰大学帕克分校数学系与科学计算与数学建模中心）
While variational autoencoders have been successful in several tasks, the use of conventional priors are limited in their ability to encode the underlying structure of input data. We introduce an Encoded Prior Sliced Wasserstein AutoEncoder wherein an additional prior-encoder network learns an embedding of the data manifold which preserves topological and geometric properties of the data, thus improving the structure of latent space. The autoencoder and prior-encoder networks are iteratively trained using the Sliced Wasserstein distance. The effectiveness of the learned manifold encoding is ex…
Model-free reinforcement learning has recently been shown to successfully learn navigation policies from raw sensor data. In this work, we address the problem of learning driving policies for an autonomous agent in a high-fidelity simulator. Building upon recent research that applies deep reinforcement learning to navigation problems, we present a modular deep reinforcement learning approach to predict the steering angle of the car from raw images. The first module extracts a low-dimensional latent semantic representation of the image. The control module trained with reinforcement learning tak…
Nanjing University of Aeronautics and Astronautics（南京航空航天大学）；The University of Maryland（马里兰大学）；National University of Defense Technology（国防科技大学）
We propose improving the cross-target and cross-scene generalization of visual navigation through learning an agent that is guided by conceiving the next observations it expects to see. This is achieved by learning a variational Bayesian model, called NeoNav, which generates the next expected observations (NEO) conditioned on the current observations of the agent and the target view. Our generative model is learned through optimizing a variational objective encompassing two key designs. First, the latent distribution is conditioned on current observations and the target view, leading to a mode…
Arizona State University（亚利桑那州立大学）；Intel Corporation（英特尔公司）
The advent of generative adversarial networks (GAN) has enabled new capabilities in synthesis, interpolation, and data augmentation heretofore considered very challenging. However, one of the common assumptions in most GAN architectures is the assumption of simple parametric latent-space distributions. While easy to implement, a simple latent-space distribution can be problematic for uses such as interpolation. This is due to distributional mismatches when samples are interpolated in the latent space. We present a straightforward formalization of this problem; using basic results from probabil…
Despite the surge of deep learning in the past decade, some users are skeptical to deploy these models in practice due to their black-box nature. Specifically, in the medical space where there are severe potential repercussions, we need to develop methods to gain confidence in the models' decisions. To this end, we propose a novel medical imaging generative adversarial framework, medXGAN (medical eXplanation GAN), to visually explain what a medical classifier focuses on in its binary predictions. By encoding domain knowledge of medical images, we are able to disentangle anatomical structure an…
National Taiwan University（台湾大学）；ASUS Intelligent Cloud Services（华硕智能云服务）；Carnegie Mellon University（卡内基梅隆大学）
Learning interpretable and interpolatable latent representations has been an emerging research direction, allowing researchers to understand and utilize the derived latent space for further applications such as visual synthesis or recognition. While most existing approaches derive an interpolatable latent space and induces smooth transition in image appearance, it is still not clear how to observe desirable representations which would contain semantic information of interest. In this paper, we aim to learn meaningful representations and simultaneously perform semantic-oriented and visually-smo…
In this work, we develop a method to generate infinite high-resolution images with diverse and complex content. It is based on a perfectly equivariant generator with synchronous interpolations in the image and latent spaces. Latent codes, when sampled, are positioned on the coordinate grid, and each pixel is computed from an interpolation of the nearby style codes. We modify the AdaIN mechanism to work in such a setup and train the generator in an adversarial setting to produce images positioned between any two latent vectors. At test time, this allows for generating complex and diverse infini…
University of Fukui（福井大学）；Wenzhou Medical University（温州医科大学）
In this paper, we present a deep generative model based method to generate diverse human motion interpolation results. We resort to the Conditional Variational Auto-Encoder (CVAE) to learn human motion conditioned on a pair of given start and end motions, by leveraging the Recurrent Neural Network (RNN) structure for both the encoder and the decoder. Additionally, we introduce a regularization loss to further promote sample diversity. Once trained, our method is able to generate multiple plausible coherent motions by repetitively sampling from the learned latent space. Experiments on the publi…
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Beihang University（北京航空航天大学）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）
The aim of this work is to use Variational Autoencoder (VAE) to learn a representation of an indoor environment that can be used for robot navigation. We use images extracted from a video, in which a camera takes a tour around a house, for training the VAE model with a 4 dimensional latent space. After the model is trained, each real frame has a corresponding representation point on manifold in the latent space, and each representation point has corresponding reconstructed image. For the navigation problem, we map the starting image and destination image to the latent space, then optimize a pa…
In Marius von Senden's Space and Sight, a newly sighted blind patient describes the experience of a corner as lemon-like, because corners "prick" sight like lemons prick the tongue. Prickliness, here, is a dimension in the feature space of sensory experience, an effect of the perceived on the perceiver that arises where the two interact. In the account of the newly sighted, an effect familiar from one interaction translates to a novel context. Perception serves as the vehicle for generalization, in that an effect shared across different experiences produces a concrete abstraction grounded in t…
