Related papers: HD-VGGT: High-Resolution Visual Geometry Transform…

Generating accurate 3D models is a challenging problem that traditionally requires explicit learning from 3D datasets using supervised learning. Although recent advances have shown promise in learning 3D models from 2D images, these methods…

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…

In this work, we introduce the Geometry-Aware Large Reconstruction Model (GeoLRM), an approach which can predict high-quality assets with 512k Gaussians and 21 input images in only 11 GB GPU memory. Previous works neglect the inherent…

The 3D visual grounding task aims to ground a natural language description to the targeted object in a 3D scene, which is usually represented in 3D point clouds. Previous works studied visual grounding under specific views. The…

The recent explosive interest on transformers has suggested their potential to become powerful "universal" models for computer vision tasks, such as classification, detection, and segmentation. While those attempts mainly study the…

Single-image super-resolution is a fundamental task for vision applications to enhance the image quality with respect to spatial resolution. If the input image contains degraded pixels, the artifacts caused by the degradation could be…

We tackle the problem of automatically reconstructing a complete 3D model of a scene from a single RGB image. This challenging task requires inferring the shape of both visible and occluded surfaces. Our approach utilizes viewer-centered,…

Novel-view synthesis (NVS) approaches play a critical role in vast scene reconstruction. However, these methods rely heavily on dense image inputs and prolonged training times, making them unsuitable where computational resources are…

High-resolution representations are essential for position-sensitive vision problems, such as human pose estimation, semantic segmentation, and object detection. Existing state-of-the-art frameworks first encode the input image as a…

Vector-quantized image modeling has shown great potential in synthesizing high-quality images. However, generating high-resolution images remains a challenging task due to the quadratic computational overhead of the self-attention process.…

3D GAN inversion aims to project a single image into the latent space of a 3D Generative Adversarial Network (GAN), thereby achieving 3D geometry reconstruction. While there exist encoders that achieve good results in 3D GAN inversion, they…

While 3D Gaussian Splatting (3DGS) enables high-quality, real-time rendering for bounded scenes, its extension to large-scale urban environments gives rise to critical challenges in terms of geometric consistency, memory efficiency, and…

In addition to color and textural information, geometry provides important cues for 3D scene reconstruction. However, current reconstruction methods only include geometry at the feature level thus not fully exploiting the geometric…

Achieving high-quality High Dynamic Range (HDR) imaging on resource-constrained edge devices is a critical challenge in computer vision, as its performance directly impacts downstream tasks such as intelligent surveillance and autonomous…

In this paper, we propose UniGS, a unified map representation and differentiable framework for high-fidelity multimodal 3D reconstruction based on 3D Gaussian Splatting. Our framework integrates a CUDA-accelerated rasterization pipeline…

Semantic segmentation from very fine resolution (VFR) urban scene images plays a significant role in several application scenarios including autonomous driving, land cover classification, and urban planning, etc. However, the tremendous…

We present Multiscale Vision Transformers (MViT) for video and image recognition, by connecting the seminal idea of multiscale feature hierarchies with transformer models. Multiscale Transformers have several channel-resolution scale…

3D Gaussian Splatting (3DGS) has demonstrated impressive Novel View Synthesis (NVS) results in a real-time rendering manner. During training, it relies heavily on the average magnitude of view-space positional gradients to grow Gaussians to…

Novel view synthesis (NVS) and surface reconstruction (SR) are essential tasks in 3D Gaussian Splatting (3D-GS). Despite recent progress, these tasks are often addressed independently, with GS-based rendering methods struggling under…

Deep CNN-based methods have so far achieved the state of the art results in multi-view 3D object reconstruction. Despite the considerable progress, the two core modules of these methods - multi-view feature extraction and fusion, are…