Related papers: GeRM: A Generative Rendering Model From Physically…
Multi-agent collaboration enhances the perception capabilities of individual agents through information sharing. However, in real-world applications, differences in sensors and models across heterogeneous agents inevitably lead to domain…
Towards the aim of generalized robotic manipulation, spatial generalization is the most fundamental capability that requires the policy to work robustly under different spatial distribution of objects, environment and agent itself. To…
Conditional text-to-image generation is an active area of research, with many possible applications. Existing research has primarily focused on generating a single image from available conditioning information in one step. One practical…
How to generate the ground-truth (GT) image is a critical issue for training realistic image super-resolution (Real-ISR) models. Existing methods mostly take a set of high-resolution (HR) images as GTs and apply various degradations to…
Motion Transfer is a technique that synthesizes videos by transferring motion dynamics from a driving video to a source image. In this work we propose a deep learning-based framework to enable real-time video motion transfer which is…
In architecture and computer-aided design, wireframes (i.e., line-based models) are widely used as basic 3D models for design evaluation and fast design iterations. However, unlike a full design file, a wireframe model lacks critical…
Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents. Existing approaches…
Recent advancements in controllable text-to-image (T2I) diffusion models, such as Ctrl-X and FreeControl, have demonstrated robust spatial and appearance control without requiring auxiliary module training. However, these models often…
Masked Autoregressive (MAR) models promise better efficiency in visual generation than autoregressive (AR) models for the ability of parallel generation, yet their acceleration potential remains constrained by the modeling complexity of…
Graphic design images consist of multiple editable layers, such as text, background, and decorative elements, while most generative models produce rasterized outputs without explicit layer structures, limiting downstream editing. Existing…
Semantic segmentation is a crucial image understanding task, where each pixel of image is categorized into a corresponding label. Since the pixel-wise labeling for ground-truth is tedious and labor intensive, in practical applications, many…
Recent advancements in text-to-image generation have been propelled by the development of diffusion models and multi-modality learning. However, since text is typically represented sequentially in these models, it often falls short in…
Diffusion models have revitalized the image generation domain, playing crucial roles in both academic research and artistic expression. With the emergence of new diffusion models, assessing the performance of text-to-image models has become…
Generalizable neural surface reconstruction techniques have attracted great attention in recent years. However, they encounter limitations of low confidence depth distribution and inaccurate surface reasoning due to the oversimplified…
Flow-based generative super-resolution (SR) models learn to produce a diverse set of feasible SR solutions, called the SR space. Diversity of SR solutions increases with the temperature ($\tau$) of latent variables, which introduces random…
Diffusion models have shown impressive performance in many domains. However, the model's capability to follow natural language instructions (e.g., spatial relationships between objects, generating complex scenes) is still unsatisfactory. In…
While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…
Rendering 3D human appearance from a single image in real-time is crucial for achieving holographic communication and immersive VR/AR. Existing methods either rely on multi-camera setups or are constrained to offline operations. In this…
The modern computer graphics pipeline can synthesize images at remarkable visual quality; however, it requires well-defined, high-quality 3D content as input. In this work, we explore the use of imperfect 3D content, for instance, obtained…
Aligning video generative models with human preferences remains challenging: current approaches rely on Vision-Language Models (VLMs) for reward modeling, but these models struggle to capture subtle temporal dynamics. We propose a…