Related papers: A Single Image and Multimodality Is All You Need f…

Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit limitations in accurately reconstructing far-range regions.…

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

Recent single-view 3D generative methods have made significant advancements by leveraging knowledge distilled from extensive 3D object datasets. However, challenges persist in the synthesis of 3D scenes from a single view, primarily due to…

Single-image super-resolution (SISR) remains challenging due to the inherent difficulty of recovering fine-grained details and preserving perceptual quality from low-resolution inputs. Existing methods often rely on limited image priors,…

Current 4D generation methods have achieved noteworthy efficacy with the aid of advanced diffusion generative models. However, these methods lack multi-view spatial-temporal modeling and encounter challenges in integrating diverse prior…

Novel View Synthesis (NVS) can reconstruct scenes from multi-view images and synthesize novel images from new viewpoints, which provides technical support for tasks such as target recognition and environmental perception. Aerial remote…

We introduce a single-view reconstruction technique of volumetric fields in which multiple light scattering effects are omnipresent, such as in clouds. We model the unknown distribution of volumetric fields using an unconditional diffusion…

Monocular Depth Estimation (MDE) is a fundamental computer vision task with important applications in 3D vision. The current mainstream MDE methods employ an encoder-decoder architecture with multi-level/scale feature processing. However,…

We propose a new view synthesis method via synthesizing a 3D neural field from both single or few-view input images. To address the ill-posed nature of the image-to-3D generation problem, we devise a two-stage method that involves a…

Content creation, central to applications such as virtual reality, can be a tedious and time-consuming. Recent image synthesis methods simplify this task by offering tools to generate new views from as little as a single input image, or by…

Monocular depth estimation involves predicting depth from a single RGB image and plays a crucial role in applications such as autonomous driving, robotic navigation, 3D reconstruction, etc. Recent advancements in learning-based methods have…

Monocular depth estimation within the diffusion-denoising paradigm demonstrates impressive generalization ability but suffers from low inference speed. Recent methods adopt a single-step deterministic paradigm to improve inference…

In dynamic Neural Radiance Fields (NeRF) systems, state-of-the-art novel view synthesis methods often fail under significant viewpoint deviations, producing unstable and unrealistic renderings. To address this, we introduce Expanded Dynamic…

3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…

We propose DiffuStereo, a novel system using only sparse cameras (8 in this work) for high-quality 3D human reconstruction. At its core is a novel diffusion-based stereo module, which introduces diffusion models, a type of powerful…

Novel view synthesis from a single image has recently achieved remarkable results, although the requirement of some form of 3D, pose, or multi-view supervision at training time limits the deployment in real scenarios. This work aims at…

Taking an image of an object is at its core a lossy process. The rich information about the three-dimensional structure of the world is flattened to an image plane and decisions such as viewpoint and camera parameters are final and not…

Deep denoising models require extensive real-world training data, which is challenging to acquire. Current noise synthesis techniques struggle to accurately model complex noise distributions. We propose a novel Realistic Noise Synthesis…

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…

This paper presents an effective solution for view extrapolation in autonomous driving scenarios. Recent approaches focus on generating shifted novel view images from given viewpoints using diffusion models. However, these methods heavily…