Point clouds are widely used in various fields, including augmented reality (AR) and robotics, where relighting and texture editing are crucial for realistic visualization. Achieving these tasks requires accurately separating albedo from shade. However, performing this separation on point clouds presents two key challenges: (1) the non-grid structure of point clouds makes conventional image-based decomposition models ineffective, and (2) point-cloud models designed for other tasks do not explicitly consider global-light direction, resulting in inaccurate shade. In this paper, we introduce Intrinsic Point-Cloud Decomposition (IPCD), which extends image decomposition to the direct decomposition of colored point clouds into albedo and shade. To overcome challenge (1), we propose IPCD-Net that extends image-based model with point-wise feature aggregation for non-grid data processing. For challenge (2), we introduce Projection-based Luminance Distribution (PLD) with a hierarchical feature refinement, capturing global-light ques via multi-view projection. For comprehensive evaluation, we create a synthetic outdoor-scene dataset. Experimental results demonstrate that IPCD-Net reduces cast shadows in albedo and enhances color accuracy in shade. Furthermore, we showcase its applications in texture editing, relighting, and point-cloud registration under varying illumination. Finally, we verify the real-world applicability of IPCD-Net.

Intrinsic image decomposition (IID) is the task of separating an image into albedo and shade. In real-world scenes, it is difficult to quantitatively assess IID quality due to the unavailability of ground truth. The existing method provides the relative reflection intensities based on human-judged annotations. However, these annotations have challenges in subjectivity, relative evaluation, and hue non-assessment. To address these, we propose a concept of quantitative evaluation with a calculated albedo from a hyperspectral imaging and light detection and ranging (LiDAR) intensity. Additionally, we introduce an optional albedo densification approach based on spectral similarity. This paper conducted a concept verification in a laboratory environment, and suggested the feasibility of an objective, absolute, and hue-aware assessment.1

Unsupervised intrinsic image decomposition (IID) is the task of separating a natural image into albedo and shade without ground truth during training. Although a recent model employing light detection and ranging (LiDAR) intensity demonstrated impressive performance, the necessity of LiDAR intensity during inference restricts its practicality. To expand the usage scenario while maintaining the IID quality achieved by using both an image and its corresponding LiDAR intensity, we propose a novel approach that utilizes an image without LiDAR intensity during inference while utilizing both an image and LiDAR intensity during training. Specifically, our proposed model processes an image and LiDAR intensity individually using distinct encoder paths during training, but utilizes only an imageencoder path during inference. Additionally, we introduce an albedo-alignment loss aligning the gray-scale albedo from an image to that from its corresponding LiDAR intensity. LiDAR intensity is not affected by illumination effects including cast shadows, thus albedo-alignment loss transfers the illumination-invariant property of LiDAR intensity to the image-encoder path. Furthermore, we also propose image-LiDAR conversion (ILC) paths that mutually translates the style of an image and LiDAR intensity. IID models translate an image into albedo and shade styles while keeping the image contents, thus it is important to separate the image into contents and style. Trained with pairs of an image and its corresponding LiDAR intensity which share contents but differ in style, the mutual translation in ILC paths improve the accuracy of the separation. Consequently, our model achieves comparable IID quality to the existing model with LiDAR intensity, while utilizing only an image without LiDAR intensity during inference.

Recent advances in deep learning have improved 3D point cloud registration but increased graphics processing unit (GPU) memory usage, often requiring preliminary sampling that reduces accuracy. We propose an overlapping region sampling method to reduce memory usage while maintaining accuracy. Our approach estimates the overlapping region and intensively samples from it, using a k-nearest-neighbor (kNN) based point compression mechanism with multi layer perceptron (MLP) and transformer architectures. Evaluations on 3DMatch and 3DLoMatch datasets show our method outperforms other sampling methods in registration recall, especially at lower GPU memory levels. For 3DMatch, we achieve 94% recall with 33% reduced memory usage, with greater advantages in 3DLoMatch. Our method enables efficient large-scale point cloud registration in resource-constrained environments, maintaining high accuracy while significantly reducing memory requirements.

Manually labelling point clouds scenes for use as training data in machine learning applications is a time and labour intensive task. In this paper, we aim to reduce the effort associated with learning semantic segmentation tasks by introducing a semi -supervised method that operates on scenes with only a small number of labelled points. For this task, we advocate the use of pseudo-labelling in combination with PointNet, a neural network architecture for point cloud classification and segmentation. We also introduce a method for incorporating information derived from spatial relationships to aid in the pseudo-labelling process. This approach has practical advantages over current methods by working directly on point clouds and not being reliant on predefined features. Moreover, we demonstrate competitive performance on scenes from two publicly available datasets and provide studies on parameter sensitivity.

This paper studies clothing and attribute recognition in the fashion domain. Specifically, in this paper, we turn our attention to the compatibility of clothing items and attributes (Fig 1). For example, people do not wear a skirt and a dress at the same time, yet a jacket and a shirt are a preferred combination. We consider such inter-object or inter-attribute compatibility and formulate a Conditional Random Field (CRF) that seeks the most probable combination in the given picture. The model takes into account the location-specific appearance with respect to a human body and the semantic correlation between clothing items and attributes, which we learn using the max-margin framework. Fig 2 illustrates our pipeline. We evaluate our model using two datasets that resemble realistic applica- tion scenarios: on-line social networks and shopping sites. The empirical evaluation indicates that our model effectively improves the recognition performance over various baselines including the state-of-the-art feature designed exclusively for clothing recognition. The results also suggest that our model generalizes well to different fashion-related applications.

In this paper, we propose a novel method to detect boundaries and estimate figure/ground assignments simultaneously. The proposed approach is based on the observation that the mid-level feature expression for boundary detection can represent local shape of boundaries with high accuracy and high speed [1]. We use figure/ground information to enhance the mid-level features for occlusion boundaries, and propose an algorithm to integrate these mid-level features efficiently. In our global optimization process, efficient and accurate estimation is achieved by superpixel-based combinatorial optimization. Superpixel segmentation is used to reduce the boundary candidates while integrating neighboring classification responses reduces computation time and improves the accuracy of figure/ground assignment. Experiments show that the proposal can detect occlusion boundaries 10 times faster and conduct figure/ground assignment 7.1% more accurately than the current state-of-the-art alternative.

This paper proposes a novel method of discovering a set of image contents sharing a specific context (attributes or implicit meaning) with the help of image collections obtained from social curation platforms. Socially curated contents are promising to analyze various kinds of multimedia information, since they are manually filtered and organized based on specific individual preferences, interests or perspectives. Our proposed method fully exploits the process of social curation: (1) How image contents are manually grouped together by users, and (2) how image contents are distributed in the platform. Our method reveals the fact that image contents with a specific context are naturally grouped together and every image content includes really various contexts that cannot necessarily be verbalized by texts.% A preliminary experiment with a small collection of a million of images yields a promising result.

This paper describes a human shape reconstruction method from multiple cameras in daily living environment, which leads to robust markerless motion capture. Due to continual illumination changes in daily space, it had been difficult to get human shape by background subtraction methods. Recent statistical foreground segmentation techniques based on graph-cuts, which combine background subtraction information and image contrast, provide successful results; however, they fail to extract human shape when furniture such as tables and chairs are moved. In this paper, we focus on the results of face detectors that would be independent of such background changes and help to improve the robustness under movement of background objects. We propose a robust human shape reconstruction method with the following two characteristics. One is iterative image segmentation based on graph-cuts to integrate head position information into shape reconstruction. The other is high-precision head tracker to keep multi-view consistency. Experimental results show that proposed method has enhanced human pose estimation based on reconstructed human shape, and enables the system to deal with dynamic environment.