相关论文: Lighting-grounded Video Generation with Renderer-b…

Inspired by the remarkable success of Latent Diffusion Models (LDMs) for image synthesis, we study LDM for text-to-video generation, which is a formidable challenge due to the computational and memory constraints during both model training…

Our study introduces a new image-to-video generator called FashionFlow to generate fashion videos. By utilising a diffusion model, we are able to create short videos from still fashion images. Our approach involves developing and connecting…

We present BlenderFusion, a generative visual compositing framework that synthesizes new scenes by recomposing objects, camera, and background. It follows a layering-editing-compositing pipeline: (i) segmenting and converting visual inputs…

Manipulating the illumination of a 3D scene within a single image represents a fundamental challenge in computer vision and graphics. This problem has traditionally been addressed using inverse rendering techniques, which involve explicit…

There has been tremendous progress in large-scale text-to-image synthesis driven by diffusion models enabling versatile downstream applications such as 3D object synthesis from texts, image editing, and customized generation. We present a…

LiDAR scenes constitute a fundamental source for several autonomous driving applications. Despite the existence of several datasets, scenes from adverse weather conditions are rarely available. This limits the robustness of downstream…

Extended reality (XR) demands generative models that respond to users' tracked real-world motion, yet current video world models accept only coarse control signals such as text or keyboard input, limiting their utility for embodied…

The field of neural rendering has witnessed significant progress with advancements in generative models and differentiable rendering techniques. Though 2D diffusion has achieved success, a unified 3D diffusion pipeline remains unsettled.…

Diffusion-based methods can generate realistic images and videos, but they struggle to edit existing objects in a video while preserving their appearance over time. This prevents diffusion models from being applied to natural video editing…

Precise camera pose control is crucial for video generation with diffusion models. Existing methods require fine-tuning with additional datasets containing paired videos and camera pose annotations, which are both data-intensive and…

Language-guided scene-aware human motion generation has great significance for entertainment and robotics. In response to the limitations of existing datasets, we introduce LaserHuman, a pioneering dataset engineered to revolutionize…

Video and audio content creation serves as the core technique for the movie industry and professional users. Recently, existing diffusion-based methods tackle video and audio generation separately, which hinders the technique transfer from…

We propose VLOGGER, a method for audio-driven human video generation from a single input image of a person, which builds on the success of recent generative diffusion models. Our method consists of 1) a stochastic human-to-3d-motion…

Urban scene reconstruction from real-world observations has emerged as a powerful tool for self-driving development and testing. While current neural rendering approaches achieve high-fidelity rendering along the recorded trajectories,…

Urban scene synthesis with video generation models has recently shown great potential for autonomous driving. Existing video generation approaches to autonomous driving primarily focus on RGB video generation and lack the ability to support…

Recent advances in text-to-image generation with diffusion models present transformative capabilities in image quality. However, user controllability of the generated image, and fast adaptation to new tasks still remains an open challenge,…

The landscape of video generation is shifting, from a focus on generating visually appealing clips to building virtual environments that support interaction and maintain physical plausibility. These developments point toward the emergence…

Existing diffusion-based 3D scene generation methods primarily operate in 2D image/video latent spaces, which makes maintaining cross-view appearance and geometric consistency inherently challenging. To bridge this gap, we present OneWorld,…

We propose a novel training-free image generation algorithm that precisely controls the occlusion relationships between objects in an image. Existing image generation methods typically rely on prompts to influence occlusion, which often…

Recent remarkable advances in large-scale text-to-image diffusion models have inspired a significant breakthrough in text-to-3D generation, pursuing 3D content creation solely from a given text prompt. However, existing text-to-3D…