Multi-layer perceptrons (MLP) have proven to be effective scene encoders when combined with higher-dimensional projections of the input, commonly referred to as \textit{positional encoding}. However, scenes with a wide frequency spectrum remain a challenge: choosing high frequencies for positional encoding introduces noise in low structure areas, while low frequencies result in poor fitting of detailed regions. To address this, we propose a progressive positional encoding, exposing a hierarchical MLP structure to incremental sets of frequency encodings. Our model accurately reconstructs scenes with wide frequency bands and learns a scene representation at progressive level of detail \textit{without explicit per-level supervision}. The architecture is modular: each level encodes a continuous implicit representation that can be leveraged separately for its respective resolution, meaning a smaller network for coarser reconstructions. Experiments on several 2D and 3D datasets show improvements in reconstruction accuracy, representational capacity and training speed compared to baselines.
University of Science and Technology of China（中国科学技术大学）
Scene text removal (STR) contains two processes: text localization and background reconstruction. Through integrating both processes into a single network, previous methods provide an implicit erasure guidance by modifying all pixels in the entire image. However, there exists two problems: 1) the implicit erasure guidance causes the excessive erasure to non-text areas; 2) the one-stage erasure lacks the exhaustive removal of text region. In this paper, we propose a ProgrEssively Region-based scene Text eraser (PERT), introducing an explicit erasure guidance and performing balanced multi-stage …
Most of the existing semantic segmentation approaches with image-level class labels as supervision, highly rely on the initial class activation map (CAM) generated from the standard classification network. In this paper, a novel "Progressive Patch Learning" approach is proposed to improve the local details extraction of the classification, producing the CAM better covering the whole object rather than only the most discriminative regions as in CAMs obtained in conventional classification models. "Patch Learning" destructs the feature maps into patches and independently processes each local pat…
From Coarse to Continuous: Progressive Refinement Implicit Neural Representation for Motion-Robust Anisotropic MRI Reconstruction
Department of Bioengineering and Imperial-X, Imperial College London（生物工程系和Imperial-X，帝国理工学院伦敦分校）；Department of Bioengineering, Imperial College London（生物工程系，帝国理工学院伦敦分校）
This work presents a generative adversarial architecture for generating three-dimensional shapes based on signed distance representations. While the deep generation of shapes has been mostly tackled by voxel and surface point cloud approaches, our generator learns to approximate the signed distance for any point in space given prior latent information. Although structurally similar to generative point cloud approaches, this formulation can be evaluated with arbitrary point density during inference, leading to fine-grained details in generated outputs. Furthermore, we study the effects of using…
We propose a universal image reconstruction method to represent detailed images purely from binary sparse edge and flat color domain. Inspired by the procedures of painting, our framework, based on generative adversarial network, consists of three phases: Imitation Phase aims at initializing networks, followed by Generating Phase to reconstruct preliminary images. Moreover, Refinement Phase is utilized to fine-tune preliminary images into final outputs with details. This framework allows our model generating abundant high frequency details from sparse input information. We also explore the def…
University of Amsterdam（阿姆斯特丹大学）；DUniversum（3D宇宙公司）；AkzoNobel（阿克苏诺贝尔）
Intrinsic image decomposition (IID) is an under-constrained problem. Therefore, traditional approaches use hand crafted priors to constrain the problem. However, these constraints are limited when coping with complex scenes. Deep learning-based approaches learn these constraints implicitly through the data, but they often suffer from dataset biases (due to not being able to include all possible imaging conditions). In this paper, a combination of the two is proposed. Component specific priors like semantics and invariant features are exploited to obtain semantically and physically plausible re…
Progressively Deformable 2D Gaussian Splatting for Video Representation at Arbitrary Resolutions
Shanghai Jiao Tong University, Shanghai, China（上海交通大学）；University of Missouri--Kansas City, Kansas City, MO, USA（密苏里大学-堪萨斯城分校）；University of Canterbury, Christchurch, New Zealand（坎特伯雷大学）
Sat-DN: Implicit Surface Reconstruction from Multi-View Satellite Images with Depth and Normal Supervision
School of Remote Sensing Information Engineering, Wuhan University（遥感信息工程学院，武汉大学）；State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University（测绘遥感信息工程国家重点实验室，武汉大学）
We introduce Multiresolution Deep Implicit Functions (MDIF), a hierarchical representation that can recover fine geometry detail, while being able to perform global operations such as shape completion. Our model represents a complex 3D shape with a hierarchy of latent grids, which can be decoded into different levels of detail and also achieve better accuracy. For shape completion, we propose latent grid dropout to simulate partial data in the latent space and therefore defer the completing functionality to the decoder side. This along with our multires design significantly improves the shape …
University of Tübingen（图宾根大学）；Wilhelm-Schickard-Institute for Computer Science（威廉·席卡德计算机科学研究所）
Implicit Neural Representations (INR) use multilayer perceptrons to represent high-frequency functions in low-dimensional problem domains. Recently these representations achieved state-of-the-art results on tasks related to complex 3D objects and scenes. A core problem is the representation of highly detailed signals, which is tackled using networks with periodic activation functions (SIRENs) or applying Fourier mappings to the input. This work analyzes the connection between the two methods and shows that a Fourier mapped perceptron is structurally like one hidden layer SIREN. Furthermore, we…
Implicit neural representations (INR) have gained significant popularity for signal and image representation for many end-tasks, such as superresolution, 3D modeling, and more. Most INR architectures rely on sinusoidal positional encoding, which accounts for high-frequency information in data. However, the finite encoding size restricts the model's representational power. Higher representational power is needed to go from representing a single given image to representing large and diverse datasets. Our approach addresses this gap by representing an image with a polynomial function and eliminat…
Zhejiang University（浙江大学）；University of Bristol（布里斯托大学）；SenseTime（商汤科技）
Virtual content creation and interaction play an important role in modern 3D applications such as AR and VR. Recovering detailed 3D models from real scenes can significantly expand the scope of its applications and has been studied for decades in the computer vision and computer graphics community. We propose Vox-Surf, a voxel-based implicit surface representation. Our Vox-Surf divides the space into finite bounded voxels. Each voxel stores geometry and appearance information in its corner vertices. Vox-Surf is suitable for almost any scenario thanks to sparsity inherited from voxel representa…
We propose a probabilistic shape completion method extended to the continuous geometry of large-scale 3D scenes. Real-world scans of 3D scenes suffer from a considerable amount of missing data cluttered with unsegmented objects. The problem of shape completion is inherently ill-posed, and high-quality result requires scalable solutions that consider multiple possible outcomes. We employ the Generative Cellular Automata that learns the multi-modal distribution and transform the formulation to process large-scale continuous geometry. The local continuous shape is incrementally generated as a spa…
Let Your Image Move with Your Motion! -- Implicit Multi-Object Multi-Motion Transfer
Tianjin University（天津大学）；University of New South Wales（新南威尔士大学）；University of Electronic Science and Technology of China（电子科技大学）；Hainan University（海南大学）；University of Auckland（奥克兰大学）
ARDepth: Auto-regressive Monocular Depth Estimation with Progressive Visual Conditioning
School of Computer Science and Engineering, Sun Yat-sen University（中山大学计算机科学与工程学院）；Shenzhen Loop Area Institute（深圳河套学院）；Guangdong Key Laboratory of Big Data Analysis and Processing（广东省大数据分析与处理重点实验室）；Baidu Inc.（百度公司）；LightSpeed Studios, Tencent America（美国光速工作室，腾讯）；School of Computer Science and Artificial Intelligence, Lanzhou University of Technology（兰州理工大学计算机科学与人工智能学院）
Unsupervised Anomaly Detection on Implicit Shape representations for Sarcopenia Detection
CNRS（法国国家科学研究中心）；LS2N（南特数字科学实验室）；Movement - Interactions - Performance（运动-互动-表现研究所）；IP UR 4334 UFR STAPS（体育与运动科学学院）；CHU Nantes（南特大学医院）；INSERM（法国国家健康与医学研究院）；l’institut du thorax（胸部研究所）；Institut Universitaire de France (IUF)（法国大学研究院）
FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography
Hefei University of Technology（合肥工业大学）；Hefei Comprehensive National Science Center（合肥综合性国家科学中心）；MBZUAI（穆罕默德·本·扎耶德人工智能大学）；University of Science and Technology Beijing（北京科技大学）；Great Bay University（大湾区大学）
Quantization has been applied to multiple domains in Deep Neural Networks (DNNs). We propose Depthwise Quantization (DQ) where $\textit{quantization}$ is applied to a decomposed sub-tensor along the $\textit{feature axis}$ of weak statistical dependence. The feature decomposition leads to an exponential increase in $\textit{representation capacity}$ with a linear increase in memory and parameter cost. In addition, DQ can be directly applied to existing encoder-decoder frameworks without modification of the DNN architecture. We use DQ in the context of Hierarchical Auto-Encoder and train end-to…
Artemis: Geometry-Grounded Multi-Agent Driving World Models with Shared 3D State and Progressive Memory Update
University of Oxford（牛津大学）；University of Cambridge（剑桥大学）；University of Twente（特文特大学）；National University of Singapore（新加坡国立大学）；University of Bath（巴斯大学）
Deep Implicit Functions (DIFs) represent 3D geometry with continuous signed distance functions learned through deep neural nets. Recently DIFs-based methods have been proposed to handle shape reconstruction and dense point correspondences simultaneously, capturing semantic relationships across shapes of the same class by learning a DIFs-modeled shape template. These methods provide great flexibility and accuracy in reconstructing 3D shapes and inferring correspondences. However, the point correspondences built from these methods do not intrinsically preserve the topology of the shapes, unlike …
Texture-preserving implicit neural representation for Cone beam CT truncated reconstruction
National Key Research and Development Program of China（中华人民共和国国家重点研发计划）；National Natural Science Foundation of China（中华人民共和国国家自然科学基金）；Fundamental Research Funds for the Central Universities（中央高校基本科研业务费）
University of Twente（特文特大学）；Amsterdam UMC（阿姆斯特丹大学医学中心）；Vrije Universiteit Amsterdam（阿姆斯特丹自由大学）；Amsterdam Cardiovascular Sciences（阿姆斯特丹心血管科学研究所）
Abdominal aortic aneurysms (AAAs) are progressive dilatations of the abdominal aorta that, if left untreated, can rupture with lethal consequences. Imaging-based patient monitoring is required to select patients eligible for surgical repair. In this work, we present a model based on implicit neural representations (INRs) to model AAA progression. We represent the AAA wall over time as the zero-level set of a signed distance function (SDF), estimated by a multilayer perception that operates on space and time. We optimize this INR using automatically extracted segmentation masks in longitudinal …
SAND: Spatially Adaptive Network Depth for Fast Sampling of Neural Implicit Surfaces
Shandong University China；City University of Hong Kong China；Hong Kong University of Science；The University of Hong Kong China；Texas A\&M University USA；Shandong University；City University of Hong Kong；The University of Hong Kong；Texas A\&M University
Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction
School of Automation and Intelligent Sensing, Shanghai Jiao Tong University（上海交通大学自动化与智能感知学院）；Carnegie Mellon University（卡内基梅隆大学）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）
Understanding the Implicit User Intention via Reasoning with Large Language Model for Image Editing
Southern University of Science and Technology, Shenzhen, China（南方科技大学）；Johns Hopkins University, Baltimore, USA（约翰霍普金斯大学）；Pengcheng Laboratory, Shenzhen, China（鹏城实验室）
CASA-SDF: Curriculum-Aware Spatial Adaptation with Curvature-Guided Density for Neural Implicit Surface Reconstruction
School of Computer Science and Engineering, Nanjing University of Science and Technology（南京理工大学计算机科学与工程学院）；School of Automation, Nanjing University of Science and Technology（南京理工大学自动化学院）
Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation
Northwestern Polytechnical University（西北工业大学）；Peking University（北京大学）；The Chinese University of Hong Kong（香港中文大学）；Shanghai AI Lab（上海人工智能实验室）；The Hong Kong University of Science and Technology（香港科技大学）
Tampere University of Technology（坦佩雷理工大学）；Noiseless Imaging Ltd（Noiseless Imaging有限公司）
We introduce a paradigm for nonlocal sparsity reinforced deep convolutional neural network denoising. It is a combination of a local multiscale denoising by a convolutional neural network (CNN) based denoiser and a nonlocal denoising based on a nonlocal filter (NLF) exploiting the mutual similarities between groups of patches. CNN models are leveraged with noise levels that progressively decrease at every iteration of our framework, while their output is regularized by a nonlocal prior implicit within the NLF. Unlike complicated neural networks that embed the nonlocality prior within the layer…
Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Facebook AI Research（Facebook人工智能研究院）；National University of Singapore（新加坡国立大学）
Photo-realistic free-viewpoint rendering of real-world scenes using classical computer graphics techniques is challenging, because it requires the difficult step of capturing detailed appearance and geometry models. Recent studies have demonstrated promising results by learning scene representations that implicitly encode both geometry and appearance without 3D supervision. However, existing approaches in practice often show blurry renderings caused by the limited network capacity or the difficulty in finding accurate intersections of camera rays with the scene geometry. Synthesizing high-reso…
