Related papers: PositionIC: Unified Position and Identity Consiste…
Diffusion-based technologies have made significant strides, particularly in personalized and customized facialgeneration. However, existing methods face challenges in achieving high-fidelity and detailed identity (ID)consistency, primarily…
Personalized text-to-image generation aims to integrate specific identities into arbitrary contexts. However, existing tuning-free methods typically employ Spatially Uniform Visual Injection, causing identity features to contaminate…
This article addresses the obstacle avoidance problem for setpoint stabilization and path-following tasks in complex dynamic 2D environments that go beyond conventional scenes with isolated convex obstacles. A combined motion planner and…
We introduce the Multi-Instance Generation (MIG) task, which focuses on generating multiple instances within a single image, each accurately placed at predefined positions with attributes such as category, color, and shape, strictly…
Visual attention mechanisms have proven to be integrally important constituent components of many modern deep neural architectures. They provide an efficient and effective way to utilize visual information selectively, which has shown to be…
Attentional mechanisms are order-invariant. Positional encoding is a crucial component to allow attention-based deep model architectures such as Transformer to address sequences or images where the position of information matters. In this…
Recent thrilling progress in large-scale text-to-image (T2I) models has unlocked unprecedented synthesis quality of AI-generated content (AIGC) including image generation, 3D and video composition. Further, personalized techniques enable…
We present FoundationPose, a unified foundation model for 6D object pose estimation and tracking, supporting both model-based and model-free setups. Our approach can be instantly applied at test-time to a novel object without fine-tuning,…
The spatial attention is a straightforward approach to enhance the performance for remote sensing image captioning. However, conventional spatial attention approaches consider only the attention distribution on one fixed coarse grid,…
The Transformer-based encoder-decoder framework is becoming popular in scene text recognition, largely because it naturally integrates recognition clues from both visual and semantic domains. However, recent studies show that the two kinds…
Character image animation is gaining significant importance across various domains, driven by the demand for robust and flexible multi-subject rendering. While existing methods excel in single-person animation, they struggle to handle…
A high-performance image compression algorithm is crucial for real-time information transmission across numerous fields. Despite rapid progress in image compression, computational inefficiency and poor redundancy modeling still pose…
Despite significant progress in image captioning, generating accurate and descriptive captions remains a long-standing challenge. In this study, we propose Attention-Guided Image Captioning (AGIC), which amplifies salient visual regions…
Panoptic occupancy prediction aims to jointly infer voxel-wise semantics and instance identities within a unified 3D scene representation. Nevertheless, progress in this field remains constrained by the absence of high-quality 3D mesh…
Monocular depth estimation is fundamental for 3D scene understanding and downstream applications. However, even under the supervised setup, it is still challenging and ill-posed due to the lack of full geometric constraints. Although a…
Image-text matching tasks have recently attracted a lot of attention in the computer vision field. The key point of this cross-domain problem is how to accurately measure the similarity between the visual and the textual contents, which…
Multimodal learning often grapples with the challenge of low-quality data, which predominantly manifests as two facets: modality imbalance and noisy corruption. While these issues are often studied in isolation, we argue that they share a…
Localized subject-driven image editing aims to seamlessly integrate user-specified objects into target scenes. As generative models continue to scale, training becomes increasingly costly in terms of memory and computation, highlighting the…
Capturing user intent across heterogeneous behavioral domains stands as a fundamental challenge in session-based recommender systems. Yet, existing multi-domain approaches frequently fail to isolate the distinct contribution of cross-domain…
Novel Instance Detection and Segmentation (NIDS) aims at detecting and segmenting novel object instances given a few examples of each instance. We propose a unified, simple, yet effective framework (NIDS-Net) comprising object proposal…