Related papers: Coupled Physics-Gated Adaptation: Spatially Decodi…
In this chapter we will describe a new development of combinatorial pulsed laser deposition (CPLD) which targets the exploration of interface libraries. The idea is to modulate continuously the composition of interfaces on a few atomic…
What is the current state-of-the-art for image restoration and enhancement applied to degraded images acquired under less than ideal circumstances? Can the application of such algorithms as a pre-processing step to improve image…
Infrared and visible image fusion aim to integrate modality strengths for visually enhanced, informative images. Visible imaging in real-world scenarios is susceptible to dynamic environmental brightness fluctuations, leading to texture…
3D AI-generated content (AIGC) has made it increasingly accessible for anyone to become a 3D content creator. While recent methods leverage Score Distillation Sampling to distill 3D objects from pretrained image diffusion models, they often…
Given a visual scene, humans have strong intuitions about how a scene can evolve over time under given actions. The intuition, often termed visual intuitive physics, is a critical ability that allows us to make effective plans to manipulate…
At its core, robotic manipulation is a problem of vision-to-geometry mapping ($f(v) \rightarrow G$). Physical actions are fundamentally defined by geometric properties like 3D positions and spatial relationships. Consequently, we argue that…
Computer-Generated Holography (CGH) offers the potential for genuine, high-quality three-dimensional visuals. However, fulfilling this potential remains a practical challenge due to computational complexity and visual quality issues. We…
The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained signals are often overshadowed by dominant, high-fidelity image content (e.g., the main…
We introduce a diffusion-based framework that performs aligned novel view image and geometry generation via a warping-and-inpainting methodology. Unlike prior methods that require dense posed images or pose-embedded generative models…
Language-guided grasping has emerged as a promising paradigm for enabling robots to identify and manipulate target objects through natural language instructions, yet it remains highly challenging in cluttered or occluded scenes. Existing…
While recent video diffusion models (VDMs) produce visually impressive results, they fundamentally struggle to maintain 3D structural consistency, often resulting in object deformation or spatial drift. We hypothesize that these failures…
The rapid growth of 3D digital content necessitates expandable recognition systems for open-world scenarios. However, existing 3D class-incremental learning methods struggle under extreme data scarcity due to geometric misalignment and…
Reconstructing physically valid 3D scenes from single-view observations is a prerequisite for bridging the gap between visual perception and robotic control. However, in scenarios requiring precise contact reasoning, such as robotic…
This work presents Controllable Layer Decomposition (CLD), a method for achieving fine-grained and controllable multi-layer separation of raster images. In practical workflows, designers typically generate and edit each RGBA layer…
We provide a bridge between generative modeling in the Machine Learning community and simulated physical processes in High Energy Particle Physics by applying a novel Generative Adversarial Network (GAN) architecture to the production of…
Throughout the history of computer vision, while research has explored the integration of images (visual) and point clouds (geometric), many advancements in image and 3D object recognition have tended to process these modalities separately.…
Predicting 3D shapes and poses of static objects from a single RGB image is an important research area in modern computer vision. Its applications range from augmented reality to robotics and digital content creation. Typically this task is…
Optical flow has achieved great success under clean scenes, but suffers from restricted performance under foggy scenes. To bridge the clean-to-foggy domain gap, the existing methods typically adopt the domain adaptation to transfer the…
3D-controllable portrait synthesis has significantly advanced, thanks to breakthroughs in generative adversarial networks (GANs). However, it is still challenging to manipulate existing face images with precise 3D control. While…
We present the first systematic study of multi-domain map-to-map translation in galaxy formation simulations, leveraging deep generative models to predict diverse galactic properties. Using high-resolution magneto-hydrodynamical simulation…