Related papers: Zero123-6D: Zero-shot Novel View Synthesis for RGB…

Zero-shot learning enables models to generalise to unseen classes by leveraging semantic information, bridging the gap between training and testing sets with non-overlapping classes. While much research has focused on zero-shot learning in…

In this paper, we present KeyMatchNet, a novel network for zero-shot pose estimation in 3D point clouds. Our method uses only depth information, making it more applicable for many industrial use cases, as color information is seldom…

Most existing methods for category-level pose estimation rely on object point clouds. However, when considering transparent objects, depth cameras are usually not able to capture meaningful data, resulting in point clouds with severe…

Operating effectively in novel real-world environments requires robotic systems to estimate and interact with previously unseen objects. Current state-of-the-art models address this challenge by using large amounts of training data and…

We consider the problem of category-level 6D pose estimation from a single RGB image. Our approach represents an object category as a cuboid mesh and learns a generative model of the neural feature activations at each mesh vertex to perform…

Synthesizing multi-view 3D from one single image is a significant but challenging task. Zero-1-to-3 methods have achieved great success by lifting a 2D latent diffusion model to the 3D scope. The target view image is generated with a…

A core capability for robot manipulation is reasoning over where and how to stably place objects in cluttered environments. Traditionally, robots have relied on object-specific, hand-crafted heuristics in order to perform such reasoning,…

Bin-picking is a practical and challenging robotic manipulation task, where accurate 6D pose estimation plays a pivotal role. The workpieces in bin-picking are typically textureless and randomly stacked in a bin, which poses a significant…

Document dewarping aims to rectify deformations in photographic document images, thus improving text readability, which has attracted much attention and made great progress, but it is still challenging to preserve document structures. Given…

Novel view synthesis (NVS) from a single image is highly ill-posed due to large unobserved regions, especially for views that deviate significantly from the input. While existing methods focus on consistency between the source and generated…

We present Stable Video 3D (SV3D) -- a latent video diffusion model for high-resolution, image-to-multi-view generation of orbital videos around a 3D object. Recent work on 3D generation propose techniques to adapt 2D generative models for…

Category-level 6D pose estimation, aiming to predict the location and orientation of unseen object instances, is fundamental to many scenarios such as robotic manipulation and augmented reality, yet still remains unsolved. Precisely…

This paper investigates the use of large-scale diffusion models for Zero-Shot Video Object Segmentation (ZS-VOS) without fine-tuning on video data or training on any image segmentation data. While diffusion models have demonstrated strong…

6D pose estimation of textureless objects is a valuable but challenging task for many robotic applications. In this work, we propose a framework to address this challenge using only RGB images acquired from multiple viewpoints. The core…

Understanding visual scenes is fundamental to human intelligence. While discriminative models have significantly advanced computer vision, they often struggle with compositional understanding. In contrast, recent generative text-to-image…

We present a novel diffusion-based approach for coherent 3D scene reconstruction from a single RGB image. Our method utilizes an image-conditioned 3D scene diffusion model to simultaneously denoise the 3D poses and geometries of all objects…

In this paper the argument is made that for true novel view synthesis of objects, where the object can be synthesized from any viewpoint, an explicit 3D shape representation isdesired. Our method estimates point clouds to capture the…

In this paper, we introduce an SE(3) diffusion model-based point cloud registration framework for 6D object pose estimation in real-world scenarios. Our approach formulates the 3D registration task as a denoising diffusion process, which…

Estimating the pose of objects from images is a crucial task of 3D scene understanding, and recent approaches have shown promising results on very large benchmarks. However, these methods experience a significant performance drop when…

Generating 3D scenes is a challenging open problem, which requires synthesizing plausible content that is fully consistent in 3D space. While recent methods such as neural radiance fields excel at view synthesis and 3D reconstruction, they…