The performance of 3D object detection models over point clouds highly depends on their capability of modeling local geometric patterns. Conventional point-based models exploit local patterns through a symmetric function (e.g. max pooling) or based on graphs, which easily leads to loss of fine-grained geometric structures. Regarding capturing spatial patterns, CNNs are powerful but it would be computationally costly to directly apply convolutions on point data after voxelizing the entire point clouds to a dense regular 3D grid. In this work, we aim to improve performance of point-based models by enhancing their pattern learning ability through leveraging CNNs while preserving computational efficiency. We propose a novel and principled Local Grid Rendering (LGR) operation to render the small neighborhood of a subset of input points into a low-resolution 3D grid independently, which allows small-size CNNs to accurately model local patterns and avoids convolutions over a dense grid to save computation cost. With the LGR operation, we introduce a new generic backbone called LGR-Net for point cloud feature extraction with simple design and high efficiency. We validate LGR-Net for 3D object detection on the challenging ScanNet and SUN RGB-D datasets. It advances state-of-the-art results significantly by 5.5 and 4.5 mAP, respectively, with only slight increased computation overhead.
Beijing Institute of Technology（北京理工大学）；Inception Institute of Artificial Intelligence（起源人工智能研究院）；King Abdullah University of Science and Technology（阿卜杜拉国王科技大学）；Indiana University（印第安纳大学）；University of Kentucky（肯塔基大学）
Previous works for LiDAR-based 3D object detection mainly focus on the single-frame paradigm. In this paper, we propose to detect 3D objects by exploiting temporal information in multiple frames, i.e., the point cloud videos. We empirically categorize the temporal information into short-term and long-term patterns. To encode the short-term data, we present a Grid Message Passing Network (GMPNet), which considers each grid (i.e., the grouped points) as a node and constructs a k-NN graph with the neighbor grids. To update features for a grid, GMPNet iteratively collects information from its neig…
Shanghai Jiao Tong University（上海交通大学）；Anhui University（安徽大学）；Shanghai AI Lab（上海人工智能实验室）
Recent years we have witnessed rapid development in NeRF-based image rendering due to its high quality. However, point clouds rendering is somehow less explored. Compared to NeRF-based rendering which suffers from dense spatial sampling, point clouds rendering is naturally less computation intensive, which enables its deployment in mobile computing device. In this work, we focus on boosting the image quality of point clouds rendering with a compact model design. We first analyze the adaption of the volume rendering formulation on point clouds. Based on the analysis, we simplify the NeRF repres…
We develop an effective point cloud rendering pipeline for novel view synthesis, which enables high fidelity local detail reconstruction, real-time rendering and user-friendly editing. In the heart of our pipeline is an adaptive frequency modulation module called Adaptive Frequency Net (AFNet), which utilizes a hypernetwork to learn the local texture frequency encoding that is consecutively injected into adaptive frequency activation layers to modulate the implicit radiance signal. This mechanism improves the frequency expressive ability of the network with richer frequency basis support, only…
The Chinese University of Hong Kong（香港中文大学）；SmartMore（思谋科技）
Synthesizing photo-realistic images from a point cloud is challenging because of the sparsity of point cloud representation. Recent Neural Radiance Fields and extensions are proposed to synthesize realistic images from 2D input. In this paper, we present Point2Pix as a novel point renderer to link the 3D sparse point clouds with 2D dense image pixels. Taking advantage of the point cloud 3D prior and NeRF rendering pipeline, our method can synthesize high-quality images from colored point clouds, generally for novel indoor scenes. To improve the efficiency of ray sampling, we propose point-guid…
Nanjing University of Science and Technology（南京理工大学）
Point clouds obtained from 3D sensors are usually sparse. Existing methods mainly focus on upsampling sparse point clouds in a supervised manner by using dense ground truth point clouds. In this paper, we propose a self-supervised point cloud upsampling network (SSPU-Net) to generate dense point clouds without using ground truth. To achieve this, we exploit the consistency between the input sparse point cloud and generated dense point cloud for the shapes and rendered images. Specifically, we first propose a neighbor expansion unit (NEU) to upsample the sparse point clouds, where the local geo…
University of Electronic Science and Technology of China（电子科技大学）；Google Research（谷歌研究院）；Nuro Inc（Nuro公司）
We present a new deep point cloud rendering pipeline through multi-plane projections. The input to the network is the raw point cloud of a scene and the output are image or image sequences from a novel view or along a novel camera trajectory. Unlike previous approaches that directly project features from 3D points onto 2D image domain, we propose to project these features into a layered volume of camera frustum. In this way, the visibility of 3D points can be automatically learnt by the network, such that ghosting effects due to false visibility check as well as occlusions caused by noise inte…
The Chinese University of Hong Kong（香港中文大学）；SmartMore（思谋科技）
Existing learning-based methods for point cloud rendering adopt various 3D representations and feature querying mechanisms to alleviate the sparsity problem of point clouds. However, artifacts still appear in rendered images, due to the challenges in extracting continuous and discriminative 3D features from point clouds. In this paper, we present a dense while lightweight 3D representation, named TriVol, that can be combined with NeRF to render photo-realistic images from point clouds. Our TriVol consists of triple slim volumes, each of which is encoded from the point cloud. TriVol has two adv…
Aligning partial views of a scene into a single whole is essential to understanding one's environment and is a key component of numerous robotics tasks such as SLAM and SfM. Recent approaches have proposed end-to-end systems that can outperform traditional methods by leveraging pose supervision. However, with the rising prevalence of cameras with depth sensors, we can expect a new stream of raw RGB-D data without the annotations needed for supervision. We propose UnsupervisedR&R: an end-to-end unsupervised approach to learning point cloud registration from raw RGB-D video. The key idea is to l…
Zhejiang University（浙江大学）；Max Planck Institute for Informatics（马克斯·普朗克信息学研究所）；Adobe Research（奥多比研究中心）；Shanghai AI Laboratory（上海人工智能实验室）；The Chinese University of Hong Kong（香港中文大学）
Purely MLP-based neural radiance fields (NeRF-based methods) often suffer from underfitting with blurred renderings on large-scale scenes due to limited model capacity. Recent approaches propose to geographically divide the scene and adopt multiple sub-NeRFs to model each region individually, leading to linear scale-up in training costs and the number of sub-NeRFs as the scene expands. An alternative solution is to use a feature grid representation, which is computationally efficient and can naturally scale to a large scene with increased grid resolutions. However, the feature grid tends to be…
PRED: Pre-training via Semantic Rendering on LiDAR Point Clouds
Center for Data Science, Peking University（北京大学数据科学中心）；National Key Laboratory of General Artificial Intelligence, School of Intelligence（通用人工智能全国重点实验室）；Pazhou Lab（琶洲实验室）
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）；University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
In this paper, we proposed a novel Style-based Point Generator with Adversarial Rendering (SpareNet) for point cloud completion. Firstly, we present the channel-attentive EdgeConv to fully exploit the local structures as well as the global shape in point features. Secondly, we observe that the concatenation manner used by vanilla foldings limits its potential of generating a complex and faithful shape. Enlightened by the success of StyleGAN, we regard the shape feature as style code that modulates the normalization layers during the folding, which considerably enhances its capability. Thirdly,…
We have recently seen tremendous progress in neural rendering (NR) advances, i.e., NeRF, for photo-real free-view synthesis. Yet, as a local technique based on a single computer/GPU, even the best-engineered Instant-NGP or i-NGP cannot reach real-time performance when rendering at a high resolution, and often requires huge local computing resources. In this paper, we resort to cloud rendering and present NEPHELE, a neural platform for highly realistic cloud radiance rendering. In stark contrast with existing NR approaches, our NEPHELE allows for more powerful rendering capabilities by combinin…
MBPU: A Plug-and-Play State Space Model for Point Cloud Upsamping with Fast Point Rendering
School of Computer Science, Fudan University（复旦大学计算机科学学院）；Academy for Engineering and Technology, Fudan University（复旦大学工程技术研究院）；Department of Information Engineering, The Chinese University of Hong Kong（香港中文大学信息工程系）；School of Mechanical Engineering, Tongji University（同济大学机械工程学院）
University of Tübingen（蒂宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）；Zhejiang University（浙江大学）
State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every sample along each ray leads to slow rendering. Therefore, existing approaches often render low-resolution feature maps and process them with an upsampling network to obtain the final image. Albeit efficient, neural rendering often entangles viewpoint and content such that changing the camera pose results in unwanted changes of geometry or appearance. Motivated by recent results in voxel-based novel view synthesis, we inv…
Rendering-Oriented 3D Point Cloud Attribute Compression using Sparse Tensor-based Transformer
School of Telecommunication Engineering, Xidian University（西安电子科技大学通信工程学院）；City University of Hong Kong（香港城市大学）；School of Electronics and Information, Northwestern Polytechnical University（西北工业大学电子信息学院）；School of Engineering, Royal Melbourne Institute of Technology（皇家墨尔本理工大学工程学院）
University of Tübingen（图宾根大学）；Max Planck Institute for Intelligent Systems（马克斯·普朗克智能系统研究所）
Traditional convolution layers are specifically designed to exploit the natural data representation of images -- a fixed and regular grid. However, unstructured data like 3D point clouds containing irregular neighborhoods constantly breaks the grid-based data assumption. Therefore applying best-practices and design choices from 2D-image learning methods towards processing point clouds are not readily possible. In this work, we introduce a natural generalization flex-convolution of the conventional convolution layer along with an efficient GPU implementation. We demonstrate competitive performa…
Birla Institute of Technology and Science, Pilani（皮拉尼比尔拉理工学院）；SIMTech, Agency for Science, Technology and Research（新加坡科技研究局制造技术研究所）；National University of Singapore（新加坡国立大学）
We present a neural point cloud rendering pipeline through a novel multi-frequency-aware patch adversarial learning framework. The proposed approach aims to improve the rendering realness by minimizing the spectrum discrepancy between real and synthesized images, especially on the high-frequency localized sharpness information which causes image blur visually. Specifically, a patch multi-discriminator scheme is proposed for the adversarial learning, which combines both spectral domain (Fourier Transform and Discrete Wavelet Transform) discriminators as well as the spatial (RGB) domain discrimi…
Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology（电子与计算机工程系，香港科学与技术大学）；Microelectronics Thrust, The Hong Kong University of Science and Technology (GZ)（微电子领域，香港科学与技术大学（GZ））
Carnegie Mellon University（卡内基梅隆大学）；Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室（MERL））；Clemson University（克莱姆森大学）
Recent deep networks that directly handle points in a point set, e.g., PointNet, have been state-of-the-art for supervised learning tasks on point clouds such as classification and segmentation. In this work, a novel end-to-end deep auto-encoder is proposed to address unsupervised learning challenges on point clouds. On the encoder side, a graph-based enhancement is enforced to promote local structures on top of PointNet. Then, a novel folding-based decoder deforms a canonical 2D grid onto the underlying 3D object surface of a point cloud, achieving low reconstruction errors even for objects w…
Recently, great progress has been made in 3D deep learning with the emergence of deep neural networks specifically designed for 3D point clouds. These networks are often trained from scratch or from pre-trained models learned purely from point cloud data. Inspired by the success of deep learning in the image domain, we devise a novel pre-training technique for better model initialization by utilizing the multi-view rendering of the 3D data. Our pre-training is self-supervised by a local pixel/point level correspondence loss computed from perspective projection and a global image/point cloud le…
The point cloud is gaining prominence as a method for representing 3D shapes, but its irregular format poses a challenge for deep learning methods. The common solution of transforming the data into a 3D voxel grid introduces its own challenges, mainly large memory size. In this paper we propose a novel 3D point cloud representation called 3D Modified Fisher Vectors (3DmFV). Our representation is hybrid as it combines the discrete structure of a grid with continuous generalization of Fisher vectors, in a compact and computationally efficient way. Using the grid enables us to design a new CNN ar…
CE-NPBG: Connectivity Enhanced Neural Point-Based Graphics for Novel View Synthesis in Autonomous Driving Scenes
Computer Vision Center (CVC), Universitat Autònoma de Barcelona（计算机视觉中心（CVC），巴塞罗那自治大学）；Intelligent Simulation Innovation Lab, Huawei Munich Research Center（智能仿真创新实验室，华为慕尼黑研究中心）
HKUST（香港科技大学）；Alibaba A.I. Labs（阿里巴巴人工智能实验室）；City University of Hong Kong（香港城市大学）；Simon Fraser University（西蒙弗雷泽大学）
In this work, we propose an end-to-end framework to learn local multi-view descriptors for 3D point clouds. To adopt a similar multi-view representation, existing studies use hand-crafted viewpoints for rendering in a preprocessing stage, which is detached from the subsequent descriptor learning stage. In our framework, we integrate the multi-view rendering into neural networks by using a differentiable renderer, which allows the viewpoints to be optimizable parameters for capturing more informative local context of interest points. To obtain discriminative descriptors, we also design a soft-v…
Samsung AI Center, Moscow, Russia（三星人工智能中心（莫斯科））；Skolkovo Institute of Science and Technology (Skoltech), Moscow, Russia（斯科尔科沃科学技术研究院（莫斯科））
We propose and evaluate a neural point-based graphics method that can model semi-transparent scene parts. Similarly to its predecessor pipeline, ours uses point clouds to model proxy geometry, and augments each point with a neural descriptor. Additionally, a learnable transparency value is introduced in our approach for each point. Our neural rendering procedure consists of two steps. Firstly, the point cloud is rasterized using ray grouping into a multi-channel image. This is followed by the neural rendering step that "translates" the rasterized image into an RGB output using a learnable conv…
Samsung Advanced Institute of Technology (SAIT)（三星先进技术研究院）
Temporal interpolation often plays a crucial role to learn meaningful representations in dynamic scenes. In this paper, we propose a novel method to train spatiotemporal neural radiance fields of dynamic scenes based on temporal interpolation of feature vectors. Two feature interpolation methods are suggested depending on underlying representations, neural networks or grids. In the neural representation, we extract features from space-time inputs via multiple neural network modules and interpolate them based on time frames. The proposed multi-level feature interpolation network effectively cap…
ADELE - Adaptive Delaunay Grids for High-Fidelity Mesh-Native Reconstruction
ETH Zurich（苏黎世联邦理工学院）；Beijing Institute for General Artificial Intelligence（北京通用人工智能研究院）；University of Zurich（苏黎世大学）；Balgrist University Hospital（巴尔格里斯特大学医院）
Learning Bijective Surface Parameterization for Inferring Signed Distance Functions from Sparse Point Clouds with Grid Deformation
School of Software, Tsinghua University, Beijing, China（清华大学软件学院，北京，中国）；Department of Computer Science, Wayne State University, Detroit, USA（韦恩州立大学计算机科学系，底特律，美国）
In this work we introduce a differential rendering module which allows neural networks to efficiently process cluttered data. The module is composed of continuous piecewise differentiable functions defined as a sensor array of cells embedded in 3D space. Our module is learnable and can be easily integrated into neural networks allowing to optimize data rendering towards specific learning tasks using gradient based methods in an end-to-end fashion. Essentially, the module's sensor cells are allowed to transform independently and locally focus and sense different parts of the 3D data. Thus, thro…
With the increased interest in immersive experiences, point cloud came to birth and was widely adopted as the first choice to represent 3D media. Besides several distortions that could affect the 3D content spanning from acquisition to rendering, efficient transmission of such volumetric content over traditional communication systems stands at the expense of the delivered perceptual quality. To estimate the magnitude of such degradation, employing quality metrics became an inevitable solution. In this work, we propose a novel deep-based no-reference quality metric that operates directly on the…
University of Southern California（南加州大学）；Tusimple, Inc（图森未来公司）
Due to the sparsity and irregularity of the point cloud data, methods that directly consume points have become popular. Among all point-based models, graph convolutional networks (GCN) lead to notable performance by fully preserving the data granularity and exploiting point interrelation. However, point-based networks spend a significant amount of time on data structuring (e.g., Farthest Point Sampling (FPS) and neighbor points querying), which limit the speed and scalability. In this paper, we present a method, named Grid-GCN, for fast and scalable point cloud learning. Grid-GCN uses a novel …
