Gap Completion in Point Cloud Scene occluded by Vehicles using SGC-Net

Recent advances in mobile mapping systems have greatly enhanced the efficiency and convenience of acquiring urban 3D data. These systems utilize LiDAR sensors mounted on vehicles to capture vast cityscapes. However, a significant challenge arises due to occlusions caused by roadside parked vehicles, leading to the loss of scene information, particularly on the roads, sidewalks, curbs, and the lower sections of buildings. In this study, we present a novel approach that leverages deep neural networks to learn a model capable of filling gaps in urban scenes that are obscured by vehicle occlusion. We have developed an innovative technique where we place virtual vehicle models along road boundaries in the gap-free scene and utilize a ray-casting algorithm to create a new scene with occluded gaps. This allows us to generate diverse and realistic urban point cloud scenes with and without vehicle occlusion, surpassing the limitations of real-world training data collection and annotation. Furthermore, we introduce the Scene Gap Completion Network (SGC-Net), an end-to-end model that can generate well-defined shape boundaries and smooth surfaces within occluded gaps. The experiment results reveal that 97.66% of the filled points fall within a range of 5 centimeters relative to the high-density ground truth point cloud scene. These findings underscore the efficacy of our proposed model in gap completion and reconstructing urban scenes affected by vehicle occlusions.

Test-Time Training on Graphs with Large Language Models

Graph Neural Networks have demonstrated great success in various fields of multimedia. However, the distribution shift between the training and test data challenges the effectiveness of GNNs. To mitigate this challenge, Test-Time Training (TTT) has been proposed as a promising approach. Traditional TTT methods require a demanding unsupervised training strategy to capture the information from test to benefit the main task. Inspired by the great annotation ability of Large Language Models (LLMs) on Text-Attributed Graphs (TAGs), we propose to enhance the test-time training on graphs with LLMs as annotators. In this paper, we design a novel Test-Time Training pipeline, LLMTTT, which conducts the test-time adaptation under the annotations by LLMs on a carefully-selected node set. Specifically, LLMTTT introduces a hybrid active node selection strategy that considers not only node diversity and representativeness, but also prediction signals from the pre-trained model. Given annotations from LLMs, a two-stage training strategy is designed to tailor the test-time model with the limited and noisy labels. A theoretical analysis ensures the validity of our method and extensive experiments demonstrate that the proposed LLMTTT can achieve a significant performance improvement compared to existing Out-of-Distribution (OOD) generalization methods.

BIRD: A Trustworthy Bayesian Inference Framework for Large Language Models

Large language models primarily rely on inductive reasoning for decision making. This results in unreliable decisions when applied to real-world tasks that often present incomplete contexts and conditions. Thus, accurate probability estimation and appropriate interpretations are required to enhance decision-making reliability. In this paper, we propose a Bayesian inference framework called BIRD for large language models. BIRD provides controllable and interpretable probability estimation for model decisions, based on abductive factors, LLM entailment, as well as learnable deductive Bayesian modeling. Experiments show that BIRD produces probability estimations that align with human judgments over 65% of the time using open-sourced Llama models, outperforming the state-of-the-art GPT-4 by 35%. We also show that BIRD can be directly used for trustworthy decision making on many real-world applications.

BLINK: Multimodal Large Language Models Can See but Not Perceive

We introduce Blink, a new benchmark for multimodal language models (LLMs) that focuses on core visual perception abilities not found in other evaluations. Most of the Blink tasks can be solved by humans "within a blink" (e.g., relative depth estimation, visual correspondence, forensics detection, and multi-view reasoning). However, we find these perception-demanding tasks cast significant challenges for current multimodal LLMs because they resist mediation through natural language. Blink reformats 14 classic computer vision tasks into 3,807 multiple-choice questions, paired with single or multiple images and visual prompting. While humans get 95.70% accuracy on average, Blink is surprisingly challenging for existing multimodal LLMs: even the best-performing GPT-4V and Gemini achieve accuracies of 51.26% and 45.72%, only 13.17% and 7.63% higher than random guessing, indicating that such perception abilities have not "emerged" yet in recent multimodal LLMs. Our analysis also highlights that specialist CV models could solve these problems much better, suggesting potential pathways for future improvements. We believe Blink will stimulate the community to help multimodal LLMs catch up with human-level visual perception.

DiffPoint: Single and Multi-view Point Cloud Reconstruction with ViT Based Diffusion Model

As the task of 2D-to-3D reconstruction has gained significant attention in various real-world scenarios, it becomes crucial to be able to generate high-quality point clouds. Despite the recent success of deep learning models in generating point clouds, there are still challenges in producing high-fidelity results due to the disparities between images and point clouds. While vision transformers (ViT) and diffusion models have shown promise in various vision tasks, their benefits for reconstructing point clouds from images have not been demonstrated yet. In this paper, we first propose a neat and powerful architecture called DiffPoint that combines ViT and diffusion models for the task of point cloud reconstruction. At each diffusion step, we divide the noisy point clouds into irregular patches. Then, using a standard ViT backbone that treats all inputs as tokens (including time information, image embeddings, and noisy patches), we train our model to predict target points based on input images. We evaluate DiffPoint on both single-view and multi-view reconstruction tasks and achieve state-of-the-art results. Additionally, we introduce a unified and flexible feature fusion module for aggregating image features from single or multiple input images. Furthermore, our work demonstrates the feasibility of applying unified architectures across languages and images to improve 3D reconstruction tasks.

Integrating 3D City Data through Knowledge Graphs

CityGML is a widely adopted standard by the Open Geospatial Consortium (OGC) for representing and exchanging 3D city models. The representation of semantic and topological properties in CityGML makes it possible to query such 3D city data to perform analysis in various applications, e.g., security management and emergency response, energy consumption and estimation, and occupancy measurement. However, the potential of querying CityGML data has not been fully exploited. The official GML/XML encoding of CityGML is only intended as an exchange format but is not suitable for query answering. The most common way of dealing with CityGML data is to store them in the 3DCityDB system as relational tables and then query them with the standard SQL query language. Nevertheless, for end users, it remains a challenging task to formulate queries over 3DCityDB directly for their ad-hoc analytical tasks, because there is a gap between the conceptual semantics of CityGML and the relational schema adopted in 3DCityDB. In fact, the semantics of CityGML itself can be modeled as a suitable ontology. The technology of Knowledge Graphs (KGs), where an ontology is at the core, is a good solution to bridge such a gap. Moreover, embracing KGs makes it easier to integrate with other spatial data sources, e.g., OpenStreetMap and existing (Geo)KGs (e.g., Wikidata, DBPedia, and GeoNames), and to perform queries combining information from multiple data sources. In this work, we describe a CityGML KG framework to populate the concepts in the CityGML ontology using declarative mappings to 3DCityDB, thus exposing the CityGML data therein as a KG. To demonstrate the feasibility of our approach, we use CityGML data from the city of Munich as test data and integrate OpenStreeMap data in the same area.

Generic Temporal Reasoning with Differential Analysis and Explanation

Temporal reasoning is the task of predicting temporal relations of event pairs with corresponding contexts. While some temporal reasoning models perform reasonably well on in-domain benchmarks, we have little idea of the systems' generalizability due to existing datasets' limitations. In this work, we introduce a novel task named TODAY that bridges this gap with temporal differential analysis, which as the name suggests, evaluates if systems can correctly understand the effect of incremental changes. Specifically, TODAY makes slight context changes for given event pairs, and systems need to tell how this subtle contextual change will affect temporal relation distributions. To facilitate learning, TODAY also annotates human explanations. We show that existing models, including GPT-3, drop to random guessing on TODAY, suggesting that they heavily rely on spurious information rather than proper reasoning for temporal predictions. On the other hand, we show that TODAY's supervision style and explanation annotations can be used in joint learning and encourage models to use more appropriate signals during training and outperform across several benchmarks. TODAY can also be used to train models to solicit incidental supervision from noisy sources such as GPT-3 and moves farther towards generic temporal reasoning systems.

Hybrid Multimodal Fusion for Humor Detection

In this paper, we present our solution to the MuSe-Humor sub-challenge of the Multimodal Emotional Challenge (MuSe) 2022. The goal of the MuSe-Humor sub-challenge is to detect humor and calculate AUC from audiovisual recordings of German football Bundesliga press conferences. It is annotated for humor displayed by the coaches. For this sub-challenge, we first build a discriminant model using the transformer module and BiLSTM module, and then propose a hybrid fusion strategy to use the prediction results of each modality to improve the performance of the model. Our experiments demonstrate the effectiveness of our proposed model and hybrid fusion strategy on multimodal fusion, and the AUC of our proposed model on the test set is 0.8972.

The activity-weight duality in feed forward neural networks: The geometric determinants of generalization

One of the fundamental problems in machine learning is generalization. In neural network models with a large number of weights (parameters), many solutions can be found to fit the training data equally well. The key question is which solution can describe testing data not in the training set. Here, we report the discovery of an exact duality (equivalence) between changes in activities in a given layer of neurons and changes in weights that connect to the next layer of neurons in a densely connected layer in any feed forward neural network. The activity-weight (A-W) duality allows us to map variations in inputs (data) to variations of the corresponding dual weights. By using this mapping, we show that the generalization loss can be decomposed into a sum of contributions from different eigen-directions of the Hessian matrix of the loss function at the solution in weight space. The contribution from a given eigen-direction is the product of two geometric factors (determinants): the sharpness of the loss landscape and the standard deviation of the dual weights, which is found to scale with the weight norm of the solution. Our results provide an unified framework, which we used to reveal how different regularization schemes (weight decay, stochastic gradient descent with different batch sizes and learning rates, dropout), training data size, and labeling noise affect generalization performance by controlling either one or both of these two geometric determinants for generalization. These insights can be used to guide development of algorithms for finding more generalizable solutions in overparametrized neural networks.

Determination of building flood risk maps from LiDAR mobile mapping data

With increasing urbanization, flooding is a major challenge for many cities today. Based on forecast precipitation, topography, and pipe networks, flood simulations can provide early warnings for areas and buildings at risk of flooding. Basement windows, doors, and underground garage entrances are common places where floodwater can flow into a building. Some buildings have been prepared or designed considering the threat of flooding, but others have not. Therefore, knowing the heights of these facade openings helps to identify places that are more susceptible to water ingress. However, such data is not yet readily available in most cities. Traditional surveying of the desired targets may be used, but this is a very time-consuming and laborious process. This research presents a new process for the extraction of windows and doors from LiDAR mobile mapping data. Deep learning object detection models are trained to identify these objects. Usually, this requires to provide large amounts of manual annotations. In this paper, we mitigate this problem by leveraging a rule-based method. In a first step, the rule-based method is used to generate pseudo-labels. A semi-supervised learning strategy is then applied with three different levels of supervision. The results show that using only automatically generated pseudo-labels, the learning-based model outperforms the rule-based approach by 14.6% in terms of F1-score. After five hours of human supervision, it is possible to improve the model by another 6.2%. By comparing the detected facade openings' heights with the predicted water levels from a flood simulation model, a map can be produced which assigns per-building flood risk levels. This information can be combined with flood forecasting to provide a more targeted disaster prevention guide for the city's infrastructure and residential buildings.