We present Meta 3D AssetGen (AssetGen), a significant advancement in text-to-3D generation which produces faithful, high-quality meshes with texture and material control. Compared to works that bake shading in the 3D object’s appearance, AssetGen outputs physically-based rendering (PBR) materials, supporting realistic relighting. AssetGen generates first several views of the object with separate shaded and albedo appearance channels, and then reconstructs colours, metalness and roughness in 3D, using a deferred shading loss for efficient supervision. It also uses a sign-distance function to represent 3D shape more reliably and introduces a corresponding loss for direct shape supervision. This is implemented using fused kernels for high memory efficiency. After mesh extraction, a texture refinement transformer operating in UV space significantly improves sharpness and details. AssetGen achieves 17% improvement in Chamfer Distance and 40% in LPIPS over the best concurrent work for few-view reconstruction, and a human preference of 72% over the best industry competitors of comparable speed, including those that support PBR. Project page with generated assets: https://assetgen.github.io

We introduce Replay, a collection of multi-view, multi-modal videos of humans interacting socially. Each scene is filmed in high production quality, from different view-points with several static cameras, as well as wearable action cameras, and recorded with a large array of microphones at different positions in the room. Overall, the dataset contains over 4000 minutes of footage and over 7 million timestamped high-resolution frames annotated with camera poses and partially with foreground masks. The Replay dataset has many potential applications, such as novel-view synthesis, 3D reconstruction, novel-view acoustic synthesis, human body and face analysis, and training generative models. We provide a benchmark for training and evaluating novel-view synthesis, with two scenarios of different difficulty. Finally, we evaluate several baseline state-of-the-art methods on the new benchmark.

Abstract We present a robust method to find region‐level correspondences between shapes, which are invariant to changes in geometry and applicable across multiple shape representations. We generate simplified shape graphs by jointly decomposing the shapes, and devise an adapted graph‐matching technique, from which we infer correspondences between shape regions. The simplified shape graphs are designed to primarily capture the overall structure of the shapes, without reflecting precise information about the geometry of each region, which enables us to find correspondences between shapes that might have significant geometric differences. Moreover, due to the special care we take to ensure the robustness of each part of our pipeline, our method can find correspondences between shapes with different representations, such as triangular meshes and point clouds. We demonstrate that the region‐wise matching that we obtain can be used to find correspondences between feature points, reveal the intrinsic self‐similarities of each shape and even construct point‐to‐point maps across shapes. Our method is both time and space efficient, leading to a pipeline that is significantly faster than comparable approaches. We demonstrate the performance of our approach through an extensive quantitative and qualitative evaluation on several benchmarks where we achieve comparable or superior performance to existing methods.

Abstract In this paper, we propose PCPNET, a deep‐learning based approach for estimating local 3D shape properties in point clouds. In contrast to the majority of prior techniques that concentrate on global or mid‐level attributes, e.g., for shape classification or semantic labeling, we suggest a patch‐based learning method, in which a series of local patches at multiple scales around each point is encoded in a structured manner. Our approach is especially well‐adapted for estimating local shape properties such as normals (both unoriented and oriented) and curvature from raw point clouds in the presence of strong noise and multi‐scale features. Our main contributions include both a novel multi‐scale variant of the recently proposed PointNet architecture with emphasis on local shape information, and a series of novel applications in which we demonstrate how learning from training data arising from well‐structured triangle meshes, and applying the trained model to noisy point clouds can produce superior results compared to specialized state‐of‐the‐art techniques. Finally, we demonstrate the utility of our approach in the context of shape reconstruction, by showing how it can be used to extract normal orientation information from point clouds.

Abstract In this paper we introduce a video post-processing method that enhances the rhythm of a dancing performance, in the sense that the dancing movements are more in time to the beat of the music. The dancing performance as observed in a video is analyzed and segmented into motion intervals delimited by motion beats. We present an image-space method to extract the motion beats of a video by detecting frames at which there is a significant change in direction or motion stops. The motion beats are then synchronized with the music beats such that as many beats as possible are matched with as little as possible time-warping distortion to the video. We show two applications for this cross-media synchronization: one where a given dance performance is enhanced to be better synchronized with its original music, and one where a given dance video is automatically adapted to be synchronized with different music.

Understanding semantic similarity among images is the core of a wide range of computer graphics and computer vision applications. However, the visual context of images is often ambiguous as images that can be perceived with emphasis on different attributes. In this paper, we present a method for learning the semantic visual similarity among images, inferring their latent attributes and embedding them into multi-spaces corresponding to each latent attribute. We consider the multi-embedding problem as an optimization function that evaluates the embedded distances with respect to qualitative crowdsourced clusterings. The key idea of our approach is to collect and embed qualitative pairwise tuples that share the same attributes in clusters. To ensure similarity attribute sharing among multiple measures, image classification clusters are presented to, and solved by users. The collected image clusters are then converted into groups of tuples, which are fed into our group optimization algorithm that jointly infers the attribute similarity and multi-attribute embedding. Our multi-attribute embedding allows retrieving similar objects in different attribute spaces. Experimental results show that our approach outperforms state-of-the-art multi-embedding approaches on various datasets, and demonstrate the usage of the multi-attribute embedding in image retrieval application.

We present a technique to synthesize time-varying weathered textures. Given a single texture image as input, the degree of weathering at different regions of the input texture is estimated by prevalence analysis of texture patches. This information then allows to gracefully increase or decrease the popularity of weathered patches, simulating the evolution of texture appearance both backward and forward in time. Our method can be applied to a wide variety of different textures since the reaction of the material to weathering effects is physically-oblivious and learned from the input texture itself. The weathering process evolves new structures as well as color variations, providing rich and natural results. In contrast with existing methods, our method does not require any user interaction or assistance. We demonstrate our technique on various textures, and their application to time-varying weathering of 3D scenes. We also extend our method to handle multi-layered textures, weathering transfer, and interactive weathering painting.

We present a novel system for browsing through a very large set of images according to similarity. The images are dynamically placed on a 2D canvas next to their nearest neighbors in a high-dimensional feature space. The layout and choice of images is generated on-the-fly during user interaction, reflecting the user's navigation tendencies and interests. This intuitive solution for image browsing provides a continuous experience of navigating through an infinite 2D grid arranged by similarity. In contrast to common multidimensional embedding methods, our solution does not entail an upfront creation of a full global map. Image map generation is dynamic, fast and scalable, independent of the number of images in the dataset, and seamlessly supports online updates to the dataset. Thus, the technique is a viable solution for massive and constantly varying datasets consisting of millions of images. Evaluation of our approach shows that when using DynamicMaps, users viewed many more images per minute compared to a standard relevance feedback interface, suggesting that it supports more fluid and natural interaction that enables easier and faster movement in the image space. Most users preferred DynamicMaps, indicating it is more exploratory, better supports serendipitous browsing and more fun to use

Computing similarities or distances between 3D shapes is a crucial building block for numerous tasks, including shape retrieval, exploration and classification. Current state-of-the-art distance measures mostly consider the overall appearance of the shapes and are less sensitive to fine changes in shape structure or geometry. We presentshape edit distance(SHED) that measures the amount of effort needed to transform one shape into the other, in terms of re-arranging the parts of one shape to match the parts of the other shape, as well as possibly adding and removing parts. The shape edit distance takes into account both the similarity of the overall shape structure and the similarity of individual parts of the shapes. We show that SHED is favorable to state-of-the-art distance measures in a variety of applications and datasets, and is especially successful in scenarios where detecting fine details of the shapes is important, such as shape retrieval and exploration.

We present a shape segmentation method for complete and incomplete shapes. The key idea is to directly optimize the decomposition based on a characterization of the expected geometry of a part in a shape. Rather than setting the number of parts in advance, we search for the smallest number of parts that admit the geometric characterization of the parts. The segmentation is based on an intermediate-level analysis, where first the shape is decomposed into approximate convex components, which are then merged into consistent parts based on a nonlocal geometric signature. Our method is designed to handle incomplete shapes, represented by point clouds. We show segmentation results on shapes acquired by a range scanner, and an analysis of the robustness of our method to missing regions. Moreover, our method yields results that are comparable to state-of-the-art techniques evaluated on complete shapes.

Abstract Large datasets of 3D objects require an intuitive way to browse and quickly explore shapes from the collection. We present a dynamic map of shapes where similar shapes are placed next to each other. Similarity between 3D models exists in a high dimensional space which cannot be accurately expressed in a two dimensional map. We solve this discrepancy by providing a local map with pan capabilities and a user interface that resembles an online experience of navigating through geographical maps. As the user navigates through the map, new shapes appear which correspond to the specific navigation tendencies and interests of the user, while maintaining a continuous browsing experience. In contrast with state of the art methods which typically reduce the search space by selecting constraints or employing relevance feedback, our method enables exploration of large sets without constraining the search space, allowing the user greater creativity and serendipity. A user study evaluation showed a strong preference of users for our method over a standard relevance feedback method.

We introduce an algorithm for unsupervised co-segmentation of a set of shapes so as to reveal the semantic shape parts and establish their correspondence across the set. The input set may exhibit significant shape variability where the shapes do not admit proper spatial alignment and the corresponding parts in any pair of shapes may be geometrically dissimilar. Our algorithm can handle such challenging input sets since, first, we perform co-analysis in a descriptor space , where a combination of shape descriptors relates the parts independently of their pose, location, and cardinality. Secondly, we exploit a key enabling feature of the input set, namely, dissimilar parts may be "linked" through third-parties present in the set. The links are derived from the pairwise similarities between the parts' descriptors. To reveal such linkages, which may manifest themselves as anisotropic and non-linear structures in the descriptor space, we perform spectral clustering with the aid of diffusion maps. We show that with our approach, we are able to co-segment sets of shapes that possess significant variability, achieving results that are close to those of a supervised approach.