Related papers: CamLit: Unified Video Diffusion with Explicit Came…
We present a method for harmonizing the lighting of a foreground video to match a target background scene, adjusting shadows, color tone, and illumination intensity (relightful harmonization). Unlike images, acquiring labeled data for…
Unified video modeling that combines generation and understanding capabilities is increasingly important but faces two key challenges: maintaining semantic faithfulness during flow-based generation due to text-visual token imbalance and the…
Generating high-fidelity, temporally consistent videos in autonomous driving scenarios faces a significant challenge, e.g. problematic maneuvers in corner cases. Despite recent video generation works are proposed to tackcle the mentioned…
Novel view synthesis from a single image requires inferring occluded regions of objects and scenes whilst simultaneously maintaining semantic and physical consistency with the input. Existing approaches condition neural radiance fields…
Recent advances in diffusion-based generative models have established a new paradigm for image and video relighting. However, extending these capabilities to 4D relighting remains challenging, due primarily to the scarcity of paired 4D…
In recent years, diffusion models have emerged as the most powerful approach in image synthesis. However, applying these models directly to video synthesis presents challenges, as it often leads to noticeable flickering contents. Although…
We present FloVD, a novel video diffusion model for camera-controllable video generation. FloVD leverages optical flow to represent the motions of the camera and moving objects. This approach offers two key benefits. Since optical flow can…
Single-image relighting is a challenging task that involves reasoning about the complex interplay between geometry, materials, and lighting. Many prior methods either support only specific categories of images, such as portraits, or require…
Recent single-image relighting methods, powered by advanced generative models, have achieved impressive photorealism on synthetic benchmarks. However, their effectiveness in the complex visual landscape of the real world remains largely…
With the increasing popularity of autonomous driving based on the powerful and unified bird's-eye-view (BEV) representation, a demand for high-quality and large-scale multi-view video data with accurate annotation is urgently required.…
Humans have the remarkable ability to construct consistent mental models of an environment, even under limited or varying levels of illumination. We wish to endow robots with this same capability. In this paper, we tackle the challenge of…
World models have become crucial for autonomous driving, as they learn how scenarios evolve over time to address the long-tail challenges of the real world. However, current approaches relegate world models to limited roles: they operate…
We introduce a scalable framework for novel view synthesis from RGB-D images with largely incomplete scene coverage. While generative neural approaches have demonstrated spectacular results on 2D images, they have not yet achieved similar…
Event cameras offer significant advantages for low-light video enhancement, primarily due to their high dynamic range. Current research, however, is severely limited by the absence of large-scale, real-world, and spatio-temporally aligned…
In recent years there have been remarkable breakthroughs in image-to-video generation. However, the 3D consistency and camera controllability of generated frames have remained unsolved. Recent studies have attempted to incorporate camera…
Relighting a person from a single photo is an attractive but ill-posed task, as a 2D image ambiguously entangles 3D geometry, intrinsic appearance, and illumination. Current methods either use sequential pipelines that suffer from error…
We introduce a framework that enables both multi-view character consistency and 3D camera control in video diffusion models through a novel customization data pipeline. We train the character consistency component with recorded volumetric…
We introduce a 3D-aware diffusion model, ZeroNVS, for single-image novel view synthesis for in-the-wild scenes. While existing methods are designed for single objects with masked backgrounds, we propose new techniques to address challenges…
Given a set of images of a scene, the re-rendering of this scene from novel views and lighting conditions is an important and challenging problem in Computer Vision and Graphics. On the one hand, most existing works in Computer Vision…
Novel View Synthesis (NVS) for street scenes play a critical role in the autonomous driving simulation. The current mainstream technique to achieve it is neural rendering, such as Neural Radiance Fields (NeRF) and 3D Gaussian Splatting…