Related papers: SpatialEdit: Benchmarking Fine-Grained Image Spati…
Recent advancements in foundation models, typically trained with self-supervised learning on large-scale and diverse datasets, have shown great potential in medical image analysis. However, due to the significant spatial heterogeneity of…
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…
Reliable depth estimation from spherical images is crucial for 360{\deg} vision in robotic navigation and immersive scene understanding. However, the onboard spherical camera can experience unintentional pose variations in real-world…
Text-guided image editing has recently experienced rapid development. However, simultaneously performing multiple editing actions on a single image, such as background replacement and specific subject attribute changes, while maintaining…
We propose spatially-adaptive normalization, a simple but effective layer for synthesizing photorealistic images given an input semantic layout. Previous methods directly feed the semantic layout as input to the deep network, which is then…
Text-guided human pose editing has gained significant traction in AIGC applications. However,it remains plagued by structural anomalies and generative artifacts. Existing evaluation metrics often isolate authenticity detection from quality…
Standard fine-tuning is considered not as effective as specialized methods for model editing due to its comparatively poor performance. However, it is simple, agnostic to the architectural details of the model being edited, and able to…
Image segmentation refers to the process to divide an image into nonoverlapping meaningful regions according to human perception, which has become a classic topic since the early ages of computer vision. A lot of research has been conducted…
3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the…
Despite recent progress in 3D-LLMs, they remain limited in accurately grounding language to visual and spatial elements in 3D environments. This limitation stems in part from training data that focuses on language reasoning rather than…
We present a novel framework for enhancing the visual fidelity and consistency of text-guided 3D Gaussian Splatting (3DGS) editing. Existing editing approaches face two critical challenges: inconsistent geometric reconstructions across…
Multimodal clothing image editing refers to the precise adjustment and modification of clothing images using data such as textual descriptions and visual images as control conditions, which effectively improves the work efficiency of…
While neural fields have made significant strides in view synthesis and scene reconstruction, editing them poses a formidable challenge due to their implicit encoding of geometry and texture information from multi-view inputs. In this…
Recent advances in generative adversarial networks (GANs) have shown great potentials in realistic image synthesis whereas most existing works address synthesis realism in either appearance space or geometry space but few in both. This…
We present the first text-based image editing approach for object parts based on pre-trained diffusion models. Diffusion-based image editing approaches capitalized on the deep understanding of diffusion models of image semantics to perform…
This thesis introduces "Embodied Spatial Intelligence" to address the challenge of creating robots that can perceive and act in the real world based on natural language instructions. To bridge the gap between Large Language Models (LLMs)…
Neural fields are receiving increased attention as a geometric representation due to their ability to compactly store detailed and smooth shapes and easily undergo topological changes. Compared to classic geometry representations, however,…
Spatial filtering is a commonly deployed technique to improve the quality of laser beams by optically filtering the noise. In the "textbook" example, the noise is usually assumed to be high frequency and the laser beam, Gaussian. In this…
Recently, text-guided image manipulation has received increasing attention in the research field of multimedia processing and computer vision due to its high flexibility and controllability. Its goal is to semantically manipulate parts of…
3D editing - the task of locally modifying the geometry or appearance of a 3D asset - has wide applications in immersive content creation, digital entertainment, and AR/VR. However, unlike 2D editing, it remains challenging due to the need…