Recently, 3D generative models have made impressive progress, enabling the generation of almost arbitrary 3D assets from text or image inputs. However, these approaches generate objects in isolation without any consideration for the scene where they will eventually be placed. In this paper, we propose a framework that allows for the stylization of an existing 3D asset to fit into a given 2D scene, and additionally produce a photorealistic composition as if the asset was placed within the environment. This not only opens up a new level of control for object stylization, for example, the same assets can be stylized to reflect changes in the environment, such as summer to winter or fantasy versus futuristic settings-but also makes the object-scene composition more controllable. We achieve this by combining modeling and optimizing the object's texture and environmental lighting through differentiable ray tracing with image priors from pre-trained text-to-image diffusion models. We demonstrate that our method is applicable to a wide variety of indoor and outdoor scenes and arbitrary objects.
相關內容
ACM SIGACCESS Conference on Computers and Accessibility是為殘疾人和老年人提供與計算機相關的設計、評估、使用和教育研究的首要論壇。我們歡迎提交原始的高質量的有關計算和可訪問性的主題。今年，ASSETS首次將其范圍擴大到包括關于計算機無障礙教育相關主題的原創高質量研究。官網鏈接： ·
數據集
·
contrastive
·
MoDELS
·
可約的
·
Dataset distillation methods reduce large-scale datasets to smaller sets of synthetic data, which preserve sufficient information for quickly training a new model from scratch. However, prior work on dataset distillation has focused exclusively on image classification datasets, whereas modern large-scale datasets are primarily in the vision-language space. In this work, we design the first vision-language dataset distillation method, building on the idea of trajectory matching. A key challenge is that vision-language datasets do not have a set of discrete classes. To overcome this, our proposed method jointly distills the image-text pairs in a contrastive formulation. Further, we leverage Low-Rank Adaptation (LoRA) matching to enable more efficient and effective trajectory matching in complex modern vision-language models. Since there are no existing baselines, we compare our distillation approach to three adapted vision-language coreset selection methods. We demonstrate significant improvements on the challenging Flickr30K and COCO retrieval benchmarks: for example, on Flickr30K, the best coreset selection method selecting 1000 image-text pairs for training achieves only 5.6% image-to-text retrieval accuracy (i.e., recall@1); in contrast, our dataset distillation approach almost doubles that to 9.9% with just 100 (an order of magnitude fewer) training pairs.
New algorithms for embedding graphs have reduced the asymptotic complexity of finding low-dimensional representations. One-Hot Graph Encoder Embedding (GEE) uses a single, linear pass over edges and produces an embedding that converges asymptotically to the spectral embedding. The scaling and performance benefits of this approach have been limited by a serial implementation in an interpreted language. We refactor GEE into a parallel program in the Ligra graph engine that maps functions over the edges of the graph and uses lock-free atomic instrutions to prevent data races. On a graph with 1.8B edges, this results in a 500 times speedup over the original implementation and a 17 times speedup over a just-in-time compiled version.
A confidence sequence (CS) is a sequence of confidence sets that contains a target parameter of an underlying stochastic process at any time step with high probability. This paper proposes a new approach to constructing CSs for means of bounded multivariate stochastic processes using a general gambling framework, extending the recently established coin toss framework for bounded random processes. The proposed gambling framework provides a general recipe for constructing CSs for categorical and probability-vector-valued observations, as well as for general bounded multidimensional observations through a simple reduction. This paper specifically explores the use of the mixture portfolio, akin to Cover's universal portfolio, in the proposed framework and investigates the properties of the resulting CSs. Simulations demonstrate the tightness of these confidence sequences compared to existing methods. When applied to the sampling without-replacement setting for finite categorical data, it is shown that the resulting CS based on a universal gambling strategy is provably tighter than that of the posterior-prior ratio martingale proposed by Waudby-Smith and Ramdas.
The partial Gromov-Wasserstein (PGW) problem facilitates the comparison of measures with unequal masses residing in potentially distinct metric spaces, thereby enabling unbalanced and partial matching across these spaces. In this paper, we demonstrate that the PGW problem can be transformed into a variant of the Gromov-Wasserstein problem, akin to the conversion of the partial optimal transport problem into an optimal transport problem. This transformation leads to two new solvers, mathematically and computationally equivalent, based on the Frank-Wolfe algorithm, that provide efficient solutions to the PGW problem. We further establish that the PGW problem constitutes a metric for metric measure spaces. Finally, we validate the effectiveness of our proposed solvers in terms of computation time and performance on shape-matching and positive-unlabeled learning problems, comparing them against existing baselines.
Contrastive learning often relies on comparing positive anchor samples with multiple negative samples to perform Self-Supervised Learning (SSL). However, non-contrastive approaches like BYOL, SimSiam, and Barlow Twins achieve SSL without explicit negative samples. In this paper, we introduce a unified matrix information-theoretic framework that explains many contrastive and non-contrastive learning methods. We then propose a novel method Matrix-SSL based on matrix information theory. Experimental results reveal that Matrix-SSL significantly outperforms state-of-the-art methods on the ImageNet dataset under linear evaluation settings and on MS-COCO for transfer learning tasks. Specifically, when performing 100 epochs pre-training, our method outperforms SimCLR by 4.6%, and when performing transfer learning tasks on MS-COCO, our method outperforms previous SOTA methods such as MoCo v2 and BYOL up to 3.3% with only 400 epochs compared to 800 epochs pre-training. Code available at //github.com/yifanzhang-pro/Matrix-SSL.
Video frame interpolation methodologies endeavor to create novel frames betwixt extant ones, with the intent of augmenting the video's frame frequency. However, current methods are prone to image blurring and spurious artifacts in challenging scenarios involving occlusions and discontinuous motion. Moreover, they typically rely on optical flow estimation, which adds complexity to modeling and computational costs. To address these issues, we introduce a Motion-Aware Video Frame Interpolation (MA-VFI) network, which directly estimates intermediate optical flow from consecutive frames by introducing a novel hierarchical pyramid module. It not only extracts global semantic relationships and spatial details from input frames with different receptive fields, enabling the model to capture intricate motion patterns, but also effectively reduces the required computational cost and complexity. Subsequently, a cross-scale motion structure is presented to estimate and refine intermediate flow maps by the extracted features. This approach facilitates the interplay between input frame features and flow maps during the frame interpolation process and markedly heightens the precision of the intervening flow delineations. Finally, a discerningly fashioned loss centered around an intermediate flow is meticulously contrived, serving as a deft rudder to skillfully guide the prognostication of said intermediate flow, thereby substantially refining the precision of the intervening flow mappings. Experiments illustrate that MA-VFI surpasses several representative VFI methods across various datasets, and can enhance efficiency while maintaining commendable efficacy.
Denoising diffusion probabilistic models (DDPMs) have recently taken the field of generative modeling by storm, pioneering new state-of-the-art results in disciplines such as computer vision and computational biology for diverse tasks ranging from text-guided image generation to structure-guided protein design. Along this latter line of research, methods have recently been proposed for generating 3D molecules using equivariant graph neural networks (GNNs) within a DDPM framework. However, such methods are unable to learn important geometric and physical properties of 3D molecules during molecular graph generation, as they adopt molecule-agnostic and non-geometric GNNs as their 3D graph denoising networks, which negatively impacts their ability to effectively scale to datasets of large 3D molecules. In this work, we address these gaps by introducing the Geometry-Complete Diffusion Model (GCDM) for 3D molecule generation, which outperforms existing 3D molecular diffusion models by significant margins across conditional and unconditional settings for the QM9 dataset as well as for the larger GEOM-Drugs dataset. Importantly, we demonstrate that the geometry-complete denoising process GCDM learns for 3D molecule generation allows the model to generate realistic and stable large molecules at the scale of GEOM-Drugs, whereas previous methods fail to do so with the features they learn. Additionally, we show that extensions of GCDM can not only effectively design 3D molecules for specific protein pockets but also that GCDM's geometric features can effectively be repurposed to directly optimize the geometry and chemical composition of existing 3D molecules for specific molecular properties, demonstrating new, real-world versatility of molecular diffusion models. Our source code and data are freely available at //github.com/BioinfoMachineLearning/Bio-Diffusion.
Efficient implementation of massive multiple-input-multiple-output (MIMO) transceivers is essential for the next-generation wireless networks. To reduce the high computational complexity of the massive MIMO transceiver, in this paper, we propose a new massive MIMO architecture using finite-precision arithmetic. First, we conduct the rounding error analysis and derive the lower bound of the achievable rate for single-input-multiple-output (SIMO) using maximal ratio combining (MRC) and multiple-input-single-output (MISO) systems using maximal ratio transmission (MRT) with finite-precision arithmetic. Then, considering the multi-user scenario, the rounding error analysis of zero-forcing (ZF) detection and precoding is derived by using the normal equations (NE) method. The corresponding lower bounds of the achievable sum rate are also derived and asymptotic analyses are presented. Built upon insights from these analyses and lower bounds, we propose a mixed-precision architecture for massive MIMO systems to offset performance gaps due to finite-precision arithmetic. The corresponding analysis of rounding errors and computational costs is obtained. Simulation results validate the derived bounds and underscore the superiority of the proposed mixed-precision architecture to the conventional structure.
In contrast to close-set scenarios that restore images from a predefined set of degradations, open-set image restoration aims to handle the unknown degradations that were unforeseen during the pretraining phase, which is less-touched as far as we know. In this work, we explicitly study this challenging problem and reveal its essence, i.e., the unidentified distribution shifts between test and training data. In recent, test-time adaptation emerges as a fundamental method to address this inherent disparities. Inspired by this, we propose a test-time degradation adaption framework for open-set image restoration, which involves three components, i.e., i) a pre-trained and degradation-agnostic diffusion model to generate clean images, ii) a test-time degradation adapter adapts the unknown degradations based on the input image during the testing phase, and iii) the adapter-guided image restoration guides the model through the adapter to produce the corresponding clean image. Through experiments on multiple degradations absent from the training data, we show that our method achieves comparable even better performance than those task-specific methods.
We explore the potential of a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS) to enhance the performance of wireless surveillance systems. The STAR-RIS is deployed between a full-duplex (FD) multi-antenna legitimate eavesdropper (E) and a suspicious communication pair. It reflects the suspicious signal towards the suspicious receiver (SR), while simultaneously transmitting the same signal to E for interception purposes. Additionally, it enables the forwarding of a jamming signal from E to SR, which is located on the back side of the STAR-RIS. To enhance the eavesdropping non-outage probability, we formulate a non-convex joint optimization problem to design the beamforming vectors at E and reflection/transmission phase shift matrices at the STAR-RIS. We adopt the block coordinate descent (BCD) algorithm and propose an approach, mainly based on semi-definite relaxation (SDR) and successive convex approximation (SCA), for solving the resulting decoupled sub-problems. Finally, we compare the performance of the proposed design against low-complexity zero-forcing (ZF)-based beamforming designs.
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