To read the file of this research, you can request a copy directly from the authors.
This paper proposes a lossless point cloud (PC) geometry compression method that uses neural networks to estimate the probability distribution of voxel occupancy. First, to take into account the PC sparsity, our method adaptively partitions a point cloud into multiple voxel block sizes. This partitioning is signalled via an octree. Second, we employ a deep auto-regressive generative model to estimate the occupancy probability of each voxel given the previously encoded ones. We then employ the estimated probabilities to code efficiently a block using a context-based arithmetic coder. Our context has variable size and can expand beyond the current block to learn more accurate probabilities. We also consider using data augmentation techniques to increase the generalization capability of the learned probability models, in particular in the presence of noise and lower-density point clouds. Experimental evaluation, performed on a variety of point clouds from four different datasets and with diverse characteristics, demonstrates that our method reduces significantly (by up to 30%) the rate for lossless coding compared to the state-of-the-art MPEG codec.
This article presents an overview of the recent standardization activities for point cloud compression (PCC). A point cloud is a 3D data representation used in diverse applications associated with immersive media including virtual/augmented reality, immersive telepresence, autonomous driving and cultural heritage archival. The international standard body for media compression, also known as the Motion Picture Experts Group (MPEG), is planning to release in 2020 two PCC standard specifications: video-based PCC (V-CC) and geometry-based PCC (G-PCC). V-PCC and G-PCC will be part of the ISO/IEC 23090 series on the coded representation of immersive media content. In this paper, we provide a detailed description of both codec algorithms and their coding performances. Moreover, we will also discuss certain unique aspects of point cloud compression.
Efficient point cloud compression is fundamental to enable the deployment of virtual and mixed reality applications, since the number of points to code can range in the order of millions. In this paper, we present a novel data-driven geometry compression method for static point clouds based on learned convolutional transforms and uniform quantization. We perform joint optimization of both rate and distortion using a trade-off parameter. In addition, we cast the decoding process as a binary classification of the point cloud occupancy map. Our method outperforms the MPEG reference solution in terms of rate-distortion on the Microsoft Voxelized Upper Bodies dataset with 51.5% BDBR savings on average. Moreover, while octree-based methods face exponential diminution of the number of points at low bitrates, our method still produces high resolution outputs even at low bitrates. Code and supplementary material are available at https://github.com/mauriceqch/pcc_geo_cnn .
We present a method to compress geometry information of point clouds that explores redundancies across consecutive frames of a sequence. It uses octrees and works by progressively increasing resolution of the octree. At each branch of the tree, we generate an approximation of the child nodes by a number of methods which are used as contexts to drive an arithmetic coder. The best approximation, i.e. the context that yields the least amount of encoding bits, is selected and the chosen method is indicated as side information for replication at the decoder. The core of our method is a context-based arithmetic coder in which a reference octree is used as reference to encode the current octree, thus providing 255 contexts for each output octet. The 255×255 frequency histogram is viewed as a discrete 3D surface and is conveyed to the decoder using another octree. We present two methods to generate the predictions (contexts) which use adjacent frames in the sequence (inter-frame) and one method that works purely intra-frame. The encoder continuously switches the best mode among the three and conveys such information to the decoder. Since an intra-frame prediction is present, our coder can also work in purely intra-frame mode, as well. Extensive results are presented to show the method’s potential against many compression alternatives for the geometry information in dynamic voxelized point clouds.
We describe an image compression method, consisting of a nonlinear analysis transformation, a uniform quantizer, and a nonlinear synthesis transformation. The transforms are constructed in three successive stages of convolutional linear filters and nonlinear activation functions. Unlike most convolutional neural networks, the joint nonlinearity is chosen to implement a form of local gain control, inspired by those used to model biological neurons. Using a variant of stochastic gradient descent, we jointly optimize the entire model for rate-distortion performance over a database of training images, introducing a continuous proxy for the discontinuous loss function arising from the quantizer. Under certain conditions, the relaxed loss function may be interpreted as the log likelihood of a generative model, as implemented by a variational autoencoder. Unlike these models, however, the compression model must operate at any given point along the rate-distortion curve, as specified by a trade-off parameter. Across an independent set of test images, we find that the optimized method generally exhibits better rate-distortion performance than the standard JPEG and JPEG 2000 compression methods. More importantly, we observe a dramatic improvement in visual quality for all images at all bit rates, which is supported by objective quality estimates using MS-SSIM.
We present a generic and real-time time-varying point cloud codec for 3D immersive video. This codec is suitable for mixed reality applications in which 3D point clouds are acquired at a fast rate. In this codec, intra frames are coded progressively in an octree subdivision. To further exploit inter-frame dependencies, we present an inter-prediction algorithm that partitions the octree voxel space in N × N × N macroblocks ( N=8,16,32 ). The algorithm codes points in these blocks in the predictive frame as a rigid transform applied to the points in the intra-coded frame. The rigid transform is computed using the iterative closest point algorithm and compactly represented in a quaternion quantization scheme. To encode the color attributes, we defined a mapping of color per vertex attributes in the traversed octree to an image grid and use legacy image coding method based on JPEG. As a result, a generic compression framework suitable for real-time 3D tele-immersion is developed. This framework has been optimized to run in real time on commodity hardware for both the encoder and decoder. Objective evaluation shows that a higher rate-distortion performance is achieved compared with available point cloud codecs. A subjective study in a state-of-the-art mixed reality system shows that introduced prediction distortions are negligible compared with the original reconstructed point clouds. In addition, it shows the benefit of reconstructed point cloud video as a representation in the 3D virtual world. The codec is available as open source for integration in immersive and augmented communication applications and serves as a base reference software platform in JTC1/SC29/WG11 (MPEG) for the further development of standardized point-cloud compression solutions.
3D point cloud presentation has been widely used in computer vision, automatic driving, augmented reality, smart cities and virtual reality. 3D point cloud compression method with higher compression ratio and tiny loss is the key to improve data transportation efficiency. In this paper, we propose a new 3D point cloud geometry compression method based on deep learning, also an auto-encoder performing better than other networks in detail reconstruction. It can reach much higher compression ratio than the state-of-art while keeping tolerable loss. It also supports parallel compressing multiple models by GPU, which can improve processing efficiency greatly. The compression process is composed of two parts. Firstly, Raw data is compressed into codeword by extracting feature of raw model with encoder. Then, the codeword is further compressed with sparse coding. Decompression process is implemented in reverse order. Codeword is recovered and fed into decoder to reconstruct point cloud. Detail reconstruction ability is improved by a hierarchical structure in our decoder. Latter outputs are grown from former fuzzier outputs. In this way, details are added to former output by latter layers step by step to make a more precise prediction. We compare our method with PCL compression and Draco compression on ShapeNet40 part dataset. Our method may be the first deep learning-based point cloud compression algorithm. The experiments demonstrate it is superior to former common compression algorithms with large compression ratio, which can also reserve original shapes with tiny loss.
The widespread adoption of new 3D sensor and authoring technologies has made it possible to capture 3D scenes and models in real time with decent visual quality. As an example, Microsoft's Kinect and Apple's PrimeSense technology are now being used in a wide variety of interactive 3D mobile applications, including gaming and augmented reality applications. The latest smartphones are equipped with multiple cameras, which can be readily used to generate depth images. Some of the latest smartphones also include depth-ranging sensors that can be used for 3D model generation. Light-based detection and ranging (lidar) technologies are yet another field where 3D depth acquisition is important. Realtime 3D scenery detection and ranging has become an important issue for the emerging field of autonomous navigation and driving applications.
Due to the increased popularity of augmented and virtual reality experiences, the interest in capturing the real world in multiple dimensions and in presenting it to users in an immersible fashion has never been higher. Distributing such representations enables users to freely navigate in multi-sensory 3D media experiences. Unfortunately, such representations require a large amount of data, not feasible for transmission on today’s networks. Efficient compression technologies well adopted in the content chain are in high demand and are key components to democratize augmented and virtual reality applications. The Moving Picture Experts Group, MPEG, as one of the main standardization groups dealing with multimedia, identified the trend and started recently the process of building an open standard for compactly representing 3D point clouds, which are the 3D equivalent of the very well-known 2D pixels. This paper introduces the main developments and technical aspects of this ongoing standardization effort.
This paper introduces the Deep Recurrent Attentive Writer (DRAW) neural network architecture for image generation. DRAW networks combine a novel spatial attention mechanism that mimics the foveation of the human eye, with a sequential variational auto-encoding framework that allows for the iterative construction of complex images. The system substantially improves on the state of the art for generative models on MNIST, and, when trained on the Street View House Numbers dataset, it generates images that cannot be distinguished from real data with the naked eye.
In free-viewpoint video, there is a recent trend to represent scene objects as solids rather than using multiple depth maps. Point clouds have been used in computer graphics for a long time and with the recent possibility of real time capturing and rendering, point clouds have been favored over meshes in order to save computation. Each point in the cloud is associated with its 3D position and its color. We devise a method to compress the colors in point clouds which is based on a hierarchical transform and arithmetic coding. The transform is a hierarchical sub-band transform that resembles an adaptive variation of a Haar wavelet. The arithmetic encoding of the coefficients assumes Laplace distributions, one per sub-band. The Laplace parameter for each distribution is transmitted to the decoder using a custom method. The geometry of the point cloud is encoded using the well-established octtree scanning. Results show that the proposed solution performs comparably to the current state-of-the-art, in many occasions outperforming it, while being much more computationally efficient. We believe this work represents the state-of-the-art in intra-frame compression of point clouds for real-time 3D video.
Modeling the distribution of natural images is challenging, partly because of
strong statistical dependencies which can extend over hundreds of pixels.
Recurrent neural networks have been successful in capturing long-range
dependencies in a number of problems, but only recently have found their way
into generative image models. We here introduce a recurrent image model based
on multi-dimensional long short-term memory units which are particularly suited
for image modeling due to their spatial structure. Our model scales to images
of arbitrary size and its likelihood is computationally tractable. We find that
it outperforms the state of the art in quantitative comparisons on several
image datasets and produces promising results when used for texture synthesis
We present a novel lossy compression approach for point cloud streams which exploits spatial and temporal redundancy within the point data. Our proposed compression framework can handle general point cloud streams of arbitrary and varying size, point order and point density. Furthermore, it allows for controlling coding complexity and coding precision. To compress the point clouds, we perform a spatial decomposition based on octree data structures. Additionally, we present a technique for comparing the octree data structures of consecutive point clouds. By encoding their structural differences, we can successively extend the point clouds at the decoder. In this way, we are able to detect and remove temporal redundancy from the point cloud data stream. Our experimental results show a strong compression performance of a ratio of 14 at 1 mm coordinate precision and up to 40 at a coordinate precision of 9 mm.
Inspired by theoretical results on universal modeling, a general framework for sequential modeling of gray-scale images is proposed and applied to lossless compression. The model is based on stochastic complexity considerations and is implemented with a tree structure. It is efficiently estimated by a modification of the universal algorithm context. Several variants of the algorithm are described. The sequential, lossless compression schemes obtained when the context modeler is used with an arithmetic coder are tested with a representative set of gray-scale images. The compression ratios are compared with those obtained with state-of-the-art algorithms available in the literature, with the results of the comparison consistently favoring the proposed approach.
Octree-based point-cloud compression
R. Schnabel and R. Klein, "Octree-based point-cloud compression."
Spbg, vol. 6, pp. 111-120, 2006.
Muscle: Multi sweep compression of lidar using deep entropy models
Adv Neural Inform Process Syst
S. Biswas, J. Liu, K. Wong, S. Wang, and R. Urtasun, "Muscle: Multi
sweep compression of lidar using deep entropy models," Advances in
Neural Information Processing Systems, vol. 33, 2020.
A V Oord
A. v. d. Oord, N. Kalchbrenner, and K. Kavukcuoglu, "Pixel Recurrent
Neural Networks," arXiv:1601.06759 [cs], Aug. 2016. [Online].
D P Kingma
T. Salimans, A. Karpathy, X. Chen, and D. P. Kingma, "PixelCNN++:
Improving the PixelCNN with Discretized Logistic Mixture Likelihood
and Other Modifications," arXiv:1701.05517 [cs, stat], Jan. 2017.
[Online]. Available: http://arxiv.org/abs/1701.05517
Generative adversarial nets
I J Goodfellow
I. J. Goodfellow, J. Pouget-Abadie, M. Mirza, B. Xu, D. Warde-Farley,
S. Ozair, A. Courville, and Y. Bengio, "Generative adversarial nets," in
Proceedings of the 27th International Conference on Neural Information
Processing Systems -Volume 2, ser. NIPS'14. Cambridge, MA, USA:
MIT Press, 2014, p. 2672-2680.
Learned point cloud geometry compression
J. Wang, H. Zhu, Z. Ma, T. Chen, H. Liu, and Q. Shen, "Learned point
cloud geometry compression," arXiv preprint arXiv:1909.12037, 2019.
Deep autoencoderbased lossy geometry compression for point clouds
T H Li
W. Yan, S. Liu, T. H. Li, Z. Li, G. Li et al., "Deep autoencoderbased lossy geometry compression for point clouds," arXiv preprint
3d-mininet: Learning a 2d representation from point clouds for fast and efficient 3d lidar semantic segmentation
A C Murillo
I. Alonso, L. Riazuelo, L. Montesano, and A. C. Murillo, "3d-mininet:
Learning a 2d representation from point clouds for fast and efficient 3d
lidar semantic segmentation," 2020.
Microsoft voxelized upper bodies -a voxelized point cloud dataset
S O Escolano
P A Chou
C. Loop, Q. Cai, S. O. Escolano, and P. A. Chou, "Microsoft voxelized
upper bodies -a voxelized point cloud dataset," in ISO/IEC JTC1/SC29
Joint WG11/WG1 (MPEG/JPEG) input document m38673/M72012,
8i Voxelized Full Bodies -A Voxelized Point Cloud Dataset
P A Chou
E. d'Eon, B. Harrison, T. Myers, and P. A. Chou, "8i Voxelized Full Bodies -A Voxelized Point Cloud Dataset," in
ISO/IEC JTC1/SC29 Joint WG11/WG1 (MPEG/JPEG) input document
WG11M40059/WG1M74006, Geneva, Jan. 2017.
University of sao paulo point cloud dataset
M. Zuffo, "University of sao paulo point cloud dataset," (accessed Dec
19, 2020). [Online]. Available: http://uspaulopc.di.ubi.pt
Adam: A Method for Stochastic Optimization
D P Kingma
D. P. Kingma and J. Ba, "Adam: A Method for Stochastic
Optimization," in 2015 3rd International Conference on Learning
Representations, Dec. 2014, arXiv: 1412.6980. [Online]. Available: