Related papers: Sparse multi-view hand-object reconstruction for u…
In this paper, we address the problem of detecting unseen objects from RGB images and estimating their poses in 3D. We propose two mobile friendly networks: MobilePose-Base and MobilePose-Shape. The former is used when there is only pose…
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…
This paper proposes Sparse View Synthesis. This is a view synthesis problem where the number of reference views is limited, and the baseline between target and reference view is significant. Under these conditions, current radiance field…
We present an unsupervised approach for factorizing object appearance into highlight, shading, and albedo layers, trained by multi-view real images. To do so, we construct a multi-view dataset by collecting numerous customer product photos…
We construct the first markerless deformable interaction dataset recording interactive motions of the hands and deformable objects, called HMDO (Hand Manipulation with Deformable Objects). With our built multi-view capture system, it…
Our work aims to reconstruct hand-held objects given a single RGB image. In contrast to prior works that typically assume known 3D templates and reduce the problem to 3D pose estimation, our work reconstructs generic hand-held object…
Our work aims to reconstruct a 3D object that is held and rotated by a hand in front of a static RGB camera. Previous methods that use implicit neural representations to recover the geometry of a generic hand-held object from multi-view…
The existing zero-shot detection approaches project visual features to the semantic domain for seen objects, hoping to map unseen objects to their corresponding semantics during inference. However, since the unseen objects are never…
Active object reconstruction using autonomous robots is gaining great interest. A primary goal in this task is to maximize the information of the object to be reconstructed, given limited on-board resources. Previous view planning methods…
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…
Reconstructing 3D objects from a single image remains challenging, especially under real-world occlusions. While recent diffusion-based view synthesis models can generate consistent novel views from a single RGB image, they typically assume…
Active object reconstruction is crucial for many robotic applications. A key aspect in these scenarios is generating object-specific view configurations to obtain informative measurements for reconstruction. One-shot view planning enables…
In order to function in unstructured environments, robots need the ability to recognize unseen novel objects. We take a step in this direction by tackling the problem of segmenting unseen object instances in tabletop environments. However,…
Reconstructing 3D objects is an important computer vision task that has wide application in AR/VR. Deep learning algorithm developed for this task usually relies on an unrealistic synthetic dataset, such as ShapeNet and Things3D. On the…
Reconstructing high-fidelity hand models with intricate textures plays a crucial role in enhancing human-object interaction and advancing real-world applications. Despite the state-of-the-art methods excelling in texture generation and…
Humans can infer the missing parts of an occluded object by leveraging prior knowledge and visible cues. However, enabling deep learning models to accurately predict such occluded regions remains a challenging task. De-occlusion addresses…
A fundamental problem faced by object recognition systems is that objects and their features can appear in different locations, scales and orientations. Current deep learning methods attempt to achieve invariance to local translations via…
Reconstructing detailed 3D scenes from single-view images remains a challenging task due to limitations in existing approaches, which primarily focus on geometric shape recovery, overlooking object appearances and fine shape details. To…
We propose SparseFusion, a sparse view 3D reconstruction approach that unifies recent advances in neural rendering and probabilistic image generation. Existing approaches typically build on neural rendering with re-projected features but…
It is widely accepted that optimization of imaging system performance should be guided by task-based measures of image quality (IQ). It has been advocated that imaging hardware or data-acquisition designs should be optimized by use of an…