Related papers: MDE-Edit: Masked Dual-Editing for Multi-Object Ima…

Accurate and robust object detection is critical for autonomous driving. Image-based detectors face difficulties caused by low visibility in adverse weather conditions. Thus, radar-camera fusion is of particular interest but presents…

Open-domain 3D object synthesis has been lagging behind image synthesis due to limited data and higher computational complexity. To bridge this gap, recent works have investigated multi-view diffusion but often fall short in either 3D…

In multi-object detection using neural networks, the fundamental problem is, "How should the network learn a variable number of bounding boxes in different input images?". Previous methods train a multi-object detection network through a…

Face recognition systems are increasingly vulnerable to morphing attacks, where a composite image is crafted to match multiple identities, enabling unauthorized access and identity fraud. Existing detection methods identify morphed images…

Erase inpainting, or object removal, aims to precisely remove target objects within masked regions while preserving the overall consistency of the surrounding content. Despite diffusion-based methods have made significant strides in the…

This paper aims to tackle Multiple Object Tracking (MOT), an important problem in computer vision but remains challenging due to many practical issues, especially occlusions. Indeed, we propose a new real-time Depth Perspective-aware…

The goal of scene text image super-resolution is to reconstruct high-resolution text-line images from unrecognizable low-resolution inputs. The existing methods relying on the optimization of pixel-level loss tend to yield text edges that…

Diffusion models have demonstrated their ability to generate diverse and high-quality images, sparking considerable interest in their potential for real image editing applications. However, existing diffusion-based approaches for local…

We propose ObjMST, an object-focused multimodal style transfer framework that provides separate style supervision for salient objects and surrounding elements while addressing alignment issues in multimodal representation learning. Existing…

Existing methods in Multimodal Knowledge Editing (MKE) have advanced the ability to correct outdated or inaccurate knowledge in Multimodal Large Language Models (MLLMs). However, they exhibit a critical limitation: while effectively…

Recently, text-to-image (T2I) editing has been greatly pushed forward by applying diffusion models. Despite the visual promise of the generated images, inconsistencies with the expected textual prompt remain prevalent. This paper aims to…

Autonomous driving systems rely heavily on multimodal perception data to understand complex environments. However, the long-tailed distribution of real-world data hinders generalization, especially for rare but safety-critical vehicle…

Reference-guided video editing takes a source video, a text instruction, and a reference image as inputs, requiring the model to faithfully apply the instructed edits while preserving original motion and unedited content. Existing methods…

Text-guided audio editing aims to modify specific acoustic events while strictly preserving non-target content. Despite recent progress, existing approaches remain fundamentally limited. Training-free methods often suffer from signal…

Bi-CamoDiffusion is introduced, an evolution of the CamoDiffusion framework for camouflaged object detection. It integrates edge priors into early-stage embeddings via a parameter-free injection process, which enhances boundary sharpness…

Recent advances in diffusion models have spurred research into their application for Reconstruction-based unsupervised anomaly detection. However, these methods may struggle with maintaining structural integrity and recovering the…

The Latent Diffusion Model (LDM) has demonstrated strong capabilities in high-resolution image generation and has been widely employed for Pose-Guided Person Image Synthesis (PGPIS), yielding promising results. However, the compression…

Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1)…

Creating novel images by fusing visual cues from multiple sources is a fundamental yet underexplored problem in image-to-image generation, with broad applications in artistic creation, virtual reality and visual media. Existing methods…

Lidars and cameras are critical sensors that provide complementary information for 3D detection in autonomous driving. While prevalent multi-modal methods simply decorate raw lidar point clouds with camera features and feed them directly to…