Related papers: DepR: Depth Guided Single-view Scene Reconstructio…
Depth estimation aims to predict dense depth maps. In autonomous driving scenes, sparsity of annotations makes the task challenging. Supervised models produce concave objects due to insufficient structural information. They overfit to valid…
We present iFusion, a novel 3D object reconstruction framework that requires only two views with unknown camera poses. While single-view reconstruction yields visually appealing results, it can deviate significantly from the actual object,…
DIVeR builds on the key ideas of NeRF and its variants -- density models and volume rendering -- to learn 3D object models that can be rendered realistically from small numbers of images. In contrast to all previous NeRF methods, DIVeR uses…
Reconstructing and decomposing dynamic urban scenes is crucial for autonomous driving, urban planning, and scene editing. However, existing methods fail to perform instance-aware decomposition without manual annotations, which is crucial…
Precise, object-aware control over visual content is essential for advanced image editing and compositional generation. Yet, most existing approaches operate on entire images holistically, limiting the ability to isolate and manipulate…
2D portrait animation has experienced significant advancements in recent years. Much research has utilized the prior knowledge embedded in large generative diffusion models to enhance high-quality image manipulation. However, most methods…
Despite significant progress in monocular depth estimation in the wild, recent state-of-the-art methods cannot be used to recover accurate 3D scene shape due to an unknown depth shift induced by shift-invariant reconstruction losses used in…
This paper presents PolyDiffuse, a novel structured reconstruction algorithm that transforms visual sensor data into polygonal shapes with Diffusion Models (DM), an emerging machinery amid exploding generative AI, while formulating…
We aim to tackle sparse-view reconstruction of a 360 3D scene using priors from latent diffusion models (LDM). The sparse-view setting is ill-posed and underconstrained, especially for scenes where the camera rotates 360 degrees around a…
Monocular depth estimation from a single image is an ill-posed problem for computer vision due to insufficient reliable cues as the prior knowledge. Besides the inter-frame supervision, namely stereo and adjacent frames, extensive prior…
Color-guided depth map super-resolution (CDSR) improve the spatial resolution of a low-quality depth map with the corresponding high-quality color map, benefiting various applications such as 3D reconstruction, virtual reality, and…
We present a method for dynamic surface reconstruction of large-scale urban scenes from LiDAR. Depth-based reconstructions tend to focus on small-scale objects or large-scale SLAM reconstructions that treat moving objects as outliers. We…
Reconstructing 3D objects from extremely sparse views is a long-standing and challenging problem. While recent techniques employ image diffusion models for generating plausible images at novel viewpoints or for distilling pre-trained…
We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each…
Image deblurring is an ill-posed problem with multiple plausible solutions for a given input image. However, most existing methods produce a deterministic estimate of the clean image and are trained to minimize pixel-level distortion. These…
Depth acquisition, based on active illumination, is essential for autonomous and robotic navigation. LiDARs (Light Detection And Ranging) with mechanical, fixed, sampling templates are commonly used in today's autonomous vehicles. An…
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 advancements in 3D robotic manipulation have improved grasping of everyday objects, but transparent and specular materials remain challenging due to depth sensing limitations. While several 3D reconstruction and depth completion…
Understanding and reconstructing the complex geometry and motion of dynamic scenes from video remains a formidable challenge in computer vision. This paper introduces D4RT, a simple yet powerful feedforward model designed to efficiently…
We present an approach to generate a 360-degree view of a person with a consistent, high-resolution appearance from a single input image. NeRF and its variants typically require videos or images from different viewpoints. Most existing…