Related papers: 360{\deg} Stereo Image Composition with Depth Adap…
Stereo video generation has been gaining increasing attention with recent advancements in video diffusion models. However, most existing methods focus on generating 3D stereoscopic videos from monocular 2D videos. These approaches typically…
The 3D localisation of an object and the estimation of its properties, such as shape and dimensions, are challenging under varying degrees of transparency and lighting conditions. In this paper, we propose a method for jointly localising…
The growing popularity of virtual and augmented reality communications and 360{\deg} video streaming is moving video communication systems into much more dynamic and resource-limited operating settings. The enormous data volume of 360{\deg}…
Depth estimation from a monocular 360 image is important to the perception of the entire 3D environment. However, the inherent distortion and large field of view (FoV) in 360 images pose great challenges for this task. To this end, existing…
We address the problem of reconstructing 3D surfaces from depth and surface normal maps acquired by a sensor system based on a single perspective camera. Depth and normal maps can be obtained through techniques such as structured-light…
Video object insertion is a critical task for dynamically inserting new objects into existing environments. Previous video generation methods focus primarily on synthesizing entire scenes while struggling with ensuring consistent object…
We present a stereo-matching method for depth estimation from high-resolution images using visual hulls as priors, and a memory-efficient technique for the correlation computation. Our method uses object masks extracted from supplementary…
360 cameras capture the entire surrounding environment with a large FoV, exhibiting comprehensive visual information to directly infer the 3D structures, e.g., depth and surface normal, and semantic information simultaneously. Existing…
3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has…
Jointly estimating hand and object shape facilitates the grasping task in human-to-robot handovers. However, relying on hand-crafted prior knowledge about the geometric structure of the object fails when generalising to unseen objects, and…
This paper introduces a novel deep framework for dense 3D reconstruction from multiple image frames, leveraging a sparse set of depth measurements gathered jointly with image acquisition. Given a deep multi-view stereo network, our…
Generating high-quality 360-degree views of human heads from single-view images is essential for enabling accessible immersive telepresence applications and scalable personalized content creation. While cutting-edge methods for full head…
Reconstructing dynamic 3D scenes from sparse multi-view videos is highly ill-posed, often leading to geometric collapse, trajectory drift, and floating artifacts. Recent attempts introduce generative priors to hallucinate missing content,…
Bounded by the inherent ambiguity of depth perception, contemporary multi-view 3D object detection methods fall into the performance bottleneck. Intuitively, leveraging temporal multi-view stereo (MVS) technology is the natural knowledge…
This paper presents a novel framework for converting 2D videos to immersive stereoscopic 3D, addressing the growing demand for 3D content in immersive experience. Leveraging foundation models as priors, our approach overcomes the…
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…
Stereo video retargeting aims to resize an image to a desired aspect ratio. The quality of retargeted videos can be significantly impacted by the stereo videos spatial, temporal, and disparity coherence, all of which can be impacted by the…
Despite significant progress made in the past few years, challenges remain for depth estimation using a single monocular image. First, it is nontrivial to train a metric-depth prediction model that can generalize well to diverse scenes…
In the last few years, there has been a growing interest in taking advantage of the 360 panoramic images potential, while managing the new challenges they imply. While several tasks have been improved thanks to the contextual information…
Scene reconstruction from unorganized RGB images is an important task in many computer vision applications. Multi-view Stereo (MVS) is a common solution in photogrammetry applications for the dense reconstruction of a static scene. The…