Related papers: Pixel-Perfect Visual Geometry Estimation

Existing video depth estimation faces a fundamental trade-off: generative models suffer from stochastic geometric hallucinations and scale drift, while discriminative models demand massive labeled datasets to resolve semantic ambiguities.…

Recent research explores the potential of Diffusion Models (DMs) for consistent object editing, which aims to modify object position, size, and composition, etc., while preserving the consistency of objects and background without changing…

We present the P$^3$ dataset, a large-scale multimodal benchmark for building vectorization, constructed from aerial LiDAR point clouds, high-resolution aerial imagery, and vectorized 2D building outlines, collected across three continents.…

Semantic matching aims to establish pixel-level correspondences between instances of the same category and represents a fundamental task in computer vision. Existing approaches suffer from two limitations: (i) Geometric Ambiguity: Their…

Filling cloudy pixels in multispectral satellite imagery is essential for accurate data analysis and downstream applications, especially for tasks which require time series data. To address this issue, we compare the performance of a…

Due to the diverse sparsity, high dimensionality, and large temporal variation of dynamic point clouds, it remains a challenge to design an efficient point cloud compression method. We propose to code the geometry of a given point cloud by…

3D scene generation has quickly become a challenging new research direction, fueled by consistent improvements of 2D generative diffusion models. Most prior work in this area generates scenes by iteratively stitching newly generated frames…

In this work, we propose DiT360, a DiT-based framework that performs hybrid training on perspective and panoramic data for panoramic image generation. For the issues of maintaining geometric fidelity and photorealism in generation quality,…

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…

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…

Diffusion models have attracted significant attention due to the remarkable ability to create content and generate data for tasks like image classification. However, the usage of diffusion models to generate the high-quality object…

In video-based dynamic point cloud compression (V-PCC), 3D point clouds are projected onto 2D images for compressing with the existing video codecs. However, the existing video codecs are originally designed for natural visual signals, and…

To circumvent the inherent fidelity bottlenecks and optimization misalignment of VAE-based latent diffusion, pixel-space diffusion models have emerged as a compelling end-to-end paradigm. However, existing pixel diffusion models often…

Recently, Gaussian Splatting (GS) has shown great potential for urban scene reconstruction in the field of autonomous driving. However, current urban scene reconstruction methods often depend on multimodal sensors as inputs, \textit{i.e.}…

Conventional methods of 3D object generative modeling learn volumetric predictions using deep networks with 3D convolutional operations, which are direct analogies to classical 2D ones. However, these methods are computationally wasteful in…

Generative models have achieved success in producing semantically plausible 2D images, but it remains challenging in 3D generation due to the absence of spatial geometry constraints. Typically, existing methods utilize geometric features as…

The task of image-to-multi-view generation refers to generating novel views of an instance from a single image. Recent methods achieve this by extending text-to-image latent diffusion models to multi-view version, which contains an VAE…

We investigate a challenging task of dynamic scene geometry estimation, which requires representing both spatial and temporal features. Typically, existing methods align the two features into a unified latent space to model scene geometry.…

Automatically generating a complete 3D scene from a text description, a reference image, or both has significant applications in fields like virtual reality and gaming. However, current methods often generate low-quality textures and…

The ultimate goal of many image-based modeling systems is to render photo-realistic novel views of a scene without visible artifacts. Existing evaluation metrics and benchmarks focus mainly on the geometric accuracy of the reconstructed…