Jae-Pil Heo

HPCCD: Hybrid Parallel Continuous Collision Detection using CPUs and GPUs

We present a novel, hybrid parallel continuous collision detection (HPCCD) method that exploits the availability of multi‐core CPU and GPU architectures. HPCCD is based on a bounding volume hierarchy (BVH) and selectively performs lazy reconstructions. Our method works with a wide variety of deforming models and supports self‐collision detection. HPCCD takes advantage of hybrid multi‐core architectures – using the general‐purpose CPUs to perform the BVH traversal and culling while GPUs are used to perform elementary tests that reduce to solving cubic equations. We propose a novel task decomposition method that leads to a lock‐free parallel algorithm in the main loop of our BVH‐based collision detection to create a highly scalable algorithm. By exploiting the availability of hybrid, multi‐core CPU and GPU architectures, our proposed method achieves more than an order of magnitude improvement in performance using four CPU‐cores and two GPUs, compared to using a single CPU‐core. This improvement results in an interactive performance, up to 148 fps, for various deforming benchmarks consisting of tens or hundreds of thousand triangles.

Spherical Hashing: Binary Code Embedding with Hyperspheres

Many binary code embedding schemes have been actively studied recently, since they can provide efficient similarity search, and compact data representations suitable for handling large scale image databases. Existing binary code embedding techniques encode high-dimensional data by using hyperplane-based hashing functions. In this paper we propose a novel hypersphere-based hashing function, spherical hashing, to map more spatially coherent data points into a binary code compared to hyperplane-based hashing functions. We also propose a new binary code distance function, spherical Hamming distance, tailored for our hypersphere-based binary coding scheme, and design an efficient iterative optimization process to achieve both balanced partitioning for each hash function and independence between hashing functions. Furthermore, we generalize spherical hashing to support various similarity measures defined by kernel functions. Our extensive experiments show that our spherical hashing technique significantly outperforms state-of-the-art techniques based on hyperplanes across various benchmarks with sizes ranging from one to 75 million of GIST, BoW and VLAD descriptors. The performance gains are consistent and large, up to 100 percent improvements over the second best method among tested methods. These results confirm the unique merits of using hyperspheres to encode proximity regions in high-dimensional spaces. Finally, our method is intuitive and easy to implement.

Distance Encoded Product Quantization

Many binary code embedding techniques have been proposed for large-scale approximate nearest neighbor search in computer vision. Recently, product quantization that encodes the cluster index in each subspace has been shown to provide impressive accuracy for nearest neighbor search. In this paper, we explore a simple question: is it best to use all the bit budget for encoding a cluster index in each subspace? We have found that as data points are located farther away from the centers of their clusters, the error of estimated distances among those points becomes larger. To address this issue, we propose a novel encoding scheme that distributes the available bit budget to encoding both the cluster index and the quantized distance between a point and its cluster center. We also propose two different distance metrics tailored to our encoding scheme. We have tested our method against the-state-of-the-art techniques on several well-known benchmarks, and found that our method consistently improves the accuracy over other tested methods. This result is achieved mainly because our method accurately estimates distances between two data points with the new binary codes and distance metric.

PCCD: parallel continuous collision detection

Collision detection between deformable models is one of fundamental tools of various applications including games. Collision detection can be classified into two categories: discrete and continuous collision detection methods. Discrete collision detection (DCD) has been demonstrated to show the interactive performance by using bounding volume hierarchies (BVHs). However, some colliding primitives may be missed since DCD methods find intersecting primitives only at discrete time steps. This issue can be a very serious problem in physical based simulation, CAD/CAM applications and etc. On the other hand, continuous collision detection (CCD) identifies the first time of contact of colliding primitives during a time interval between two discrete time steps.

Quadra-embedding: Binary code embedding with low quantization error

Abstract Thanks to compact data representations and fast similarity computation, many binary code embedding techniques have been proposed for large-scale similarity search used in many computer vision applications including image retrieval. Most prior techniques have centered around optimizing a set of projections for accurate embedding. In spite of active research efforts, existing solutions suffer from diminishing marginal efficiency and high quantization errors as more code bits are used. To reduce both quantization error and diminishing efficiency we propose a novel binary code embedding scheme, Quadra-Embedding, that assigns two bits for each projection to define four quantization regions, and a binary code distance function tailored to our method. Our method is directly applicable to most binary code embedding methods. Our scheme combined with four state-of-the-art embedding methods has been evaluated and achieves meaningful accuracy improvement in most experimental configurations.

Quadra-Embedding: binary code embedding with low quantization error

Thanks to compact data representations and fast similarity computation, many binary code embedding techniques have been recently proposed for large-scale similarity search used in many computer vision applications including image retrieval. Most of prior techniques have centered around optimizing a set of projections for accurate embedding. In spite of active research efforts, existing solutions suffer both from diminishing marginal efficiency as more code bits are used, and high quantization errors naturally coming from the binarization. In order to reduce both quantization error and diminishing efficiency we propose a novel binary code embedding scheme, Quadra-Embedding, that assigns two bits for each projection to define four quantization regions, and a novel binary code distance function tailored specifically to our encoding scheme. Our method is directly applicable to a wide variety of binary code embedding methods. Our scheme combined with four state-of-the-art embedding methods has been evaluated with three public image benchmarks. We have observed that our scheme achieves meaningful accuracy improvement in most experimental configurations under k- and e-NN search.

Data management for SSDs for large-scale interactive graphics applications

Solid state drives (SSDs) are emerging as an alternative storage medium to HDDs. SSDs have performance characteristics (e.g., fast random reads) that are very different from those of HDDs. Because of the high performance of SSDs, there are increasingly more research efforts to redesign the established techniques that are optimized for HDDs, to work well with SSDs. In this paper we focus on computing cache-coherent layouts of large-scale models for SSDs. It has been demonstrated that cache-oblivious layouts perform well for various applications running on HDDs. However, computing cache-oblivious layouts for large-models is known to be very expensive. Also these layouts cannot be maintained efficiently for dynamically changing models. Utilizing the properties of SSDs we propose an efficient layout computation method that produces a page-based cache-aware layout for SSDs. We show that the performance of our layout can be maintained under dynamic changes on the model and is similar to the cache-oblivious layout optimized for static models. We demonstrate the benefits of our method for large-scale walkthrough scene editing and rendering, and collision detection.

Shortlist Selection with Residual-Aware Distance Estimator for K-Nearest Neighbor Search

In this paper, we introduce a novel shortlist computation algorithm for approximate, high-dimensional nearest neighbor search. Our method relies on a novel distance estimator: the residual-aware distance estimator, that accounts for the residual distances of data points to their respective quantized centroids, and uses it for accurate short-list computation. Furthermore, we perform the residual-aware distance estimation with little additional memory and computational cost through simple pre-computation methods for inverted index and multi-index schemes. Because it modifies the initial shortlist collection phase, our new algorithm is applicable to most inverted indexing methods that use vector quantization. We have tested the proposed method with the inverted index and multi-index on a diverse set of benchmarks including up to one billion data points with varying dimensions, and found that our method robustly improves the accuracy of shortlists (up to 127% relatively higher) over the state-of-the-art techniques with a comparable or even faster computational cost.

Probabilistic cost model for nearest neighbor search in image retrieval

We present a probabilistic cost model to analyze the performance of the kd-tree for nearest neighbor search in the context of content-based image retrieval. Our cost model measures the expected number of kd-tree nodes traversed during the search query. We show that our cost model has high correlations with both the observed number of traversed nodes and the runtime performance of search queries used in image retrieval. Furthermore, we prove that, if the query points follow the distribution of data used to construct the kd-trees, the median-based partitioning method as well as PCA-based partitioning technique can produce near-optimal kd-trees in terms of minimizing our cost model. The probabilistic cost model is validated through experiments in SIFT-based image retrieval.

Rank-based voting with inclusion relationship for accurate image search

We present a rank-based voting technique utilizing inclusion relationship for high-quality image search. Since images can have multiple regions of interest, we extract representative object regions using a state-of-the-art region proposal method tailored for our search problem. We then extract CNN features locally from those representative regions and identify inclusion relationship between those regions. To identify similar images given a query, we propose a novel similarity measure based on representative regions and their inclusion relationship. Our similarity measure gives a high score to a pair of images that contain similar object regions with similar spatial arrangement. To verify benefits of our method, we test our method in three standard benchmarks and compare it against the state-of-the-art image search methods using CNN features. Our experiment results demonstrate effectiveness and robustness of the proposed algorithm.