Related papers: RealDiff: Real-world 3D Shape Completion using Sel…
Extracting keypoint locations from input hand frames, known as 3D hand pose estimation, is a critical task in various human-computer interaction applications. Essentially, the 3D hand pose estimation can be regarded as a 3D point subset…
Diffusion models have emerged as a powerful tool for point cloud generation. A key component that drives the impressive performance for generating high-quality samples from noise is iteratively denoise for thousands of steps. While…
Existing point cloud completion methods, which typically depend on predefined synthetic training datasets, encounter significant challenges when applied to out-of-distribution, real-world scans. To overcome this limitation, we introduce a…
Pseudo-LiDAR point cloud interpolation is a novel and challenging task in the field of autonomous driving, which aims to address the frequency mismatching problem between camera and LiDAR. Previous works represent the 3D spatial motion…
In this paper, we present a novel deep method to reconstruct a point cloud of an object from a single still image. Prior arts in the field struggle to reconstruct an accurate and scalable 3D model due to either the inefficient and expensive…
Accurate camera calibration is a fundamental task for 3D perception, especially when dealing with real-world, in-the-wild environments where complex optical distortions are common. Existing methods often rely on pre-rectified images or…
Reconstructing 3D models from 2D images is one of the fundamental problems in computer vision. In this work, we propose a deep learning technique for 3D object reconstruction from a single image. Contrary to recent works that either use 3D…
Generative diffusion models have shown empirical successes in point cloud resampling, generating a denser and more uniform distribution of points from sparse or noisy 3D point clouds by progressively refining noise into structure. However,…
One major challenge in 3D reconstruction is to infer the complete shape geometry from partial foreground occlusions. In this paper, we propose a method to reconstruct the complete 3D shape of an object from a single RGB image, with…
The Gaussian diffusion model, initially designed for image generation, has recently been adapted for 3D point cloud generation. However, these adaptations have not fully considered the intrinsic geometric characteristics of 3D shapes,…
We address the problem of 3D shape completion from sparse and noisy point clouds, a fundamental problem in computer vision and robotics. Recent approaches are either data-driven or learning-based: Data-driven approaches rely on a shape…
Point cloud completion aims to infer the complete geometries for missing regions of 3D objects from incomplete ones. Previous methods usually predict the complete point cloud based on the global shape representation extracted from the…
Diffusion models have recently shown promise in time series forecasting, particularly for probabilistic predictions. However, they often fail to achieve state-of-the-art point estimation performance compared to regression-based methods.…
Reconstructing the underlying 3D surface of an object from a single image is a challenging problem that has received extensive attention from the computer vision community. Many learning-based approaches tackle this problem by learning a 3D…
3D shape completion from point clouds is a challenging task, especially from scans of real-world objects. Considering the paucity of 3D shape ground truths for real scans, existing works mainly focus on benchmarking this task on synthetic…
Latent diffusion models (LDMs) have demonstrated remarkable generative capabilities across various low-level vision tasks. However, their potential for point cloud completion remains underexplored due to the unstructured and irregular…
Reference-driven image completion, which restores missing regions in a target view using additional images, is particularly challenging when the target view differs significantly from the references. Existing generative methods rely solely…
3D scene flow characterizes how the points at the current time flow to the next time in the 3D Euclidean space, which possesses the capacity to infer autonomously the non-rigid motion of all objects in the scene. The previous methods for…
Existing autoregressive (AR) methods for generating artist-designed meshes struggle to balance global structural consistency with high-fidelity local details, and are susceptible to error accumulation. To address this, we propose…
Existing LiDAR-Camera fusion methods have achieved strong results in 3D object detection. To address the sparsity of point clouds, previous approaches typically construct spatial pseudo point clouds via depth completion as auxiliary input…