SceneTAP: Scene-Coherent Typographic Adversarial Planner against Vision-Language Models in Real-World Environments

Large vision-language models (LVLMs) have shown remarkable capabilities in interpreting visual content. While existing works demonstrate these models' vulnerability to deliberately placed adversarial texts, such texts are often easily identifiable as anomalous. In this paper, we present the first approach to generate scene-coherent typographic adversarial attacks that mislead advanced LVLMs while maintaining visual naturalness through the capability of the LLM-based agent. Our approach addresses three critical questions: what adversarial text to generate, where to place it within the scene, and how to integrate it seamlessly. We propose a training-free, multi-modal LLM-driven scene-coherent typographic adversarial planning (SceneTAP) that employs a three-stage process: scene understanding, adversarial planning, and seamless integration. The SceneTAP utilizes chain-of-thought reasoning to comprehend the scene, formulate effective adversarial text, strategically plan its placement, and provide detailed instructions for natural integration within the image. This is followed by a scene-coherent TextDiffuser that executes the attack using a local diffusion mechanism. We extend our method to real-world scenarios by printing and placing generated patches in physical environments, demonstrating its practical implications. Extensive experiments show that our scene-coherent adversarial text successfully misleads state-of-the-art LVLMs, including ChatGPT-4o, even after capturing new images of physical setups. Our evaluations demonstrate a significant increase in attack success rates while maintaining visual naturalness and contextual appropriateness. This work highlights vulnerabilities in current vision-language models to sophisticated, scene-coherent adversarial attacks and provides insights into potential defense mechanisms.

Unleashing Generalization of End-to-End Autonomous Driving with Controllable Long Video Generation

Using generative models to synthesize new data has become a de-facto standard in autonomous driving to address the data scarcity issue. Though existing approaches are able to boost perception models, we discover that these approaches fail to improve the performance of planning of end-to-end autonomous driving models as the generated videos are usually less than 8 frames and the spatial and temporal inconsistencies are not negligible. To this end, we propose Delphi, a novel diffusion-based long video generation method with a shared noise modeling mechanism across the multi-views to increase spatial consistency, and a feature-aligned module to achieves both precise controllability and temporal consistency. Our method can generate up to 40 frames of video without loss of consistency which is about 5 times longer compared with state-of-the-art methods. Instead of randomly generating new data, we further design a sampling policy to let Delphi generate new data that are similar to those failure cases to improve the sample efficiency. This is achieved by building a failure-case driven framework with the help of pre-trained visual language models. Our extensive experiment demonstrates that our Delphi generates a higher quality of long videos surpassing previous state-of-the-art methods. Consequentially, with only generating 4% of the training dataset size, our framework is able to go beyond perception and prediction tasks, for the first time to the best of our knowledge, boost the planning performance of the end-to-end autonomous driving model by a margin of 25%.

LRR: Language-Driven Resamplable Continuous Representation against Adversarial Tracking Attacks

Visual object tracking plays a critical role in visual-based autonomous systems, as it aims to estimate the position and size of the object of interest within a live video. Despite significant progress made in this field, state-of-the-art (SOTA) trackers often fail when faced with adversarial perturbations in the incoming frames. This can lead to significant robustness and security issues when these trackers are deployed in the real world. To achieve high accuracy on both clean and adversarial data, we propose building a spatial-temporal continuous representation using the semantic text guidance of the object of interest. This novel continuous representation enables us to reconstruct incoming frames to maintain semantic and appearance consistency with the object of interest and its clean counterparts. As a result, our proposed method successfully defends against different SOTA adversarial tracking attacks while maintaining high accuracy on clean data. In particular, our method significantly increases tracking accuracy under adversarial attacks with around 90% relative improvement on UAV123, which is even higher than the accuracy on clean data.

Natural-language-driven Simulation Benchmark and Copilot for Efficient Production of Object Interactions in Virtual Road Scenes

We advocate the idea of the natural-language-driven(NLD) simulation to efficiently produce the object interactions between multiple objects in the virtual road scenes, for teaching and testing the autonomous driving systems that should take quick action to avoid collision with obstacles with unpredictable motions. The NLD simulation allows the brief natural-language description to control the object interactions, significantly reducing the human efforts for creating a large amount of interaction data. To facilitate the research of NLD simulation, we collect the Language-to-Interaction(L2I) benchmark dataset with 120,000 natural-language descriptions of object interactions in 6 common types of road topologies. Each description is associated with the programming code, which the graphic render can use to visually reconstruct the object interactions in the virtual scenes. As a methodology contribution, we design SimCopilot to translate the interaction descriptions to the renderable code. We use the L2I dataset to evaluate SimCopilot's abilities to control the object motions, generate complex interactions, and generalize interactions across road topologies. The L2I dataset and the evaluation results motivate the relevant research of the NLD simulation.

Open Compound Domain Adaptation with Object Style Compensation for Semantic Segmentation

Many methods of semantic image segmentation have borrowed the success of open compound domain adaptation. They minimize the style gap between the images of source and target domains, more easily predicting the accurate pseudo annotations for target domain's images that train segmentation network. The existing methods globally adapt the scene style of the images, whereas the object styles of different categories or instances are adapted improperly. This paper proposes the Object Style Compensation, where we construct the Object-Level Discrepancy Memory with multiple sets of discrepancy features. The discrepancy features in a set capture the style changes of the same category's object instances adapted from target to source domains. We learn the discrepancy features from the images of source and target domains, storing the discrepancy features in memory. With this memory, we select appropriate discrepancy features for compensating the style information of the object instances of various categories, adapting the object styles to a unified style of source domain. Our method enables a more accurate computation of the pseudo annotations for target domain's images, thus yielding state-of-the-art results on different datasets.

BEVControl: Accurately Controlling Street-view Elements with Multi-perspective Consistency via BEV Sketch Layout

Using synthesized images to boost the performance of perception models is a long-standing research challenge in computer vision. It becomes more eminent in visual-centric autonomous driving systems with multi-view cameras as some long-tail scenarios can never be collected. Guided by the BEV segmentation layouts, the existing generative networks seem to synthesize photo-realistic street-view images when evaluated solely on scene-level metrics. However, once zoom-in, they usually fail to produce accurate foreground and background details such as heading. To this end, we propose a two-stage generative method, dubbed BEVControl, that can generate accurate foreground and background contents. In contrast to segmentation-like input, it also supports sketch style input, which is more flexible for humans to edit. In addition, we propose a comprehensive multi-level evaluation protocol to fairly compare the quality of the generated scene, foreground object, and background geometry. Our extensive experiments show that our BEVControl surpasses the state-of-the-art method, BEVGen, by a significant margin, from 5.89 to 26.80 on foreground segmentation mIoU. In addition, we show that using images generated by BEVControl to train the downstream perception model, it achieves on average 1.29 improvement in NDS score.

Surface Geometry Processing: An Efficient Normal-based Detail Representation

With the rapid development of high-resolution 3D vision applications, the traditional way of manipulating surface detail requires considerable memory and computing time. To address these problems, we introduce an efficient surface detail processing framework in 2D normal domain, which extracts new normal feature representations as the carrier of micro geometry structures that are illustrated both theoretically and empirically in this article. Compared with the existing state of the arts, we verify and demonstrate that the proposed normal-based representation has three important properties, including detail separability, detail transferability and detail idempotence. Finally, three new schemes are further designed for geometric surface detail processing applications, including geometric texture synthesis, geometry detail transfer, and 3D surface super-resolution. Theoretical analysis and experimental results on the latest benchmark dataset verify the effectiveness and versatility of our normal-based representation, which accepts 30 times of the input surface vertices but at the same time only takes 6.5% memory cost and 14.0% running time in comparison with existing competing algorithms.

CVSformer: Cross-View Synthesis Transformer for Semantic Scene Completion

Semantic scene completion (SSC) requires an accurate understanding of the geometric and semantic relationships between the objects in the 3D scene for reasoning the occluded objects. The popular SSC methods voxelize the 3D objects, allowing the deep 3D convolutional network (3D CNN) to learn the object relationships from the complex scenes. However, the current networks lack the controllable kernels to model the object relationship across multiple views, where appropriate views provide the relevant information for suggesting the existence of the occluded objects. In this paper, we propose Cross-View Synthesis Transformer (CVSformer), which consists of Multi-View Feature Synthesis and Cross-View Transformer for learning cross-view object relationships. In the multi-view feature synthesis, we use a set of 3D convolutional kernels rotated differently to compute the multi-view features for each voxel. In the cross-view transformer, we employ the cross-view fusion to comprehensively learn the cross-view relationships, which form useful information for enhancing the features of individual views. We use the enhanced features to predict the geometric occupancies and semantic labels of all voxels. We evaluate CVSformer on public datasets, where CVSformer yields state-of-the-art results.

On the Robustness of Segment Anything

Segment anything model (SAM) has presented impressive objectness identification capability with the idea of prompt learning and a new collected large-scale dataset. Given a prompt (e.g., points, bounding boxes, or masks) and an input image, SAM is able to generate valid segment masks for all objects indicated by the prompts, presenting high generalization across diverse scenarios and being a general method for zero-shot transfer to downstream vision tasks. Nevertheless, it remains unclear whether SAM may introduce errors in certain threatening scenarios. Clarifying this is of significant importance for applications that require robustness, such as autonomous vehicles. In this paper, we aim to study the testing-time robustness of SAM under adversarial scenarios and common corruptions. To this end, we first build a testing-time robustness evaluation benchmark for SAM by integrating existing public datasets. Second, we extend representative adversarial attacks against SAM and study the influence of different prompts on robustness. Third, we study the robustness of SAM under diverse corruption types by evaluating SAM on corrupted datasets with different prompts. With experiments conducted on SA-1B and KITTI datasets, we find that SAM exhibits remarkable robustness against various corruptions, except for blur-related corruption. Furthermore, SAM remains susceptible to adversarial attacks, particularly when subjected to PGD and BIM attacks. We think such a comprehensive study could highlight the importance of the robustness issues of SAM and trigger a series of new tasks for SAM as well as downstream vision tasks.

Leveraging Inpainting for Single-Image Shadow Removal

Fully-supervised shadow removal methods achieve top restoration qualities on public datasets but still generate some shadow remnants. One of the reasons is the lack of large-scale shadow & shadow-free image pairs. Unsupervised methods can alleviate the issue but their restoration qualities are much lower than those of fully-supervised methods. In this work, we find that pretraining shadow removal networks on the image inpainting dataset can reduce the shadow remnants significantly: a naive encoder-decoder network gets competitive restoration quality w.r.t. the state-of-the-art methods via only 10% shadow & shadow-free image pairs. We further analyze the difference between networks with/without inpainting pretraining and observe that: inpainting pretraining enhances networks' capability of filling missed semantic information; shadow removal fine-tuning makes the networks know how to fill details of the shadow regions. Inspired by the above observations, we formulate shadow removal as a shadow-guided inpainting task to take advantage of the shadow removal and image inpainting. Specifically, we build a shadow-informed dynamic filtering network with two branches: the image inpainting branch takes the shadow-masked image as input while the second branch takes the shadow image as input and is to estimate dynamic kernels and offsets for the first branch to provide missing semantic information and details. The extensive experiments show that our method empowered with inpainting outperforms all state-of-the-art methods.