Related papers: Leveling3D: Leveling Up 3D Reconstruction with Fee…
The automatic reconstruction of 3D computer-aided design (CAD) models from CAD sketches has recently gained significant attention in the computer vision community. Most existing methods, however, rely on vector CAD sketches and 3D ground…
Reconstructing and semantically interpreting 3D scenes from sparse 2D views remains a fundamental challenge in computer vision. Conventional methods often decouple semantic understanding from reconstruction or necessitate costly per-scene…
Three-dimensional Gaussian Splatting (3DGS) has recently emerged as an efficient representation for novel-view synthesis, achieving impressive visual quality. However, in scenes dominated by large and low-texture regions, common in indoor…
3D Gaussian Splatting has recently emerged as a powerful tool for fast and accurate novel-view synthesis from a set of posed input images. However, like most novel-view synthesis approaches, it relies on accurate camera pose information,…
In this paper, we introduce Splatt3R, a pose-free, feed-forward method for in-the-wild 3D reconstruction and novel view synthesis from stereo pairs. Given uncalibrated natural images, Splatt3R can predict 3D Gaussian Splats without…
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…
High-fidelity visual reconstruction and novel-view synthesis are essential for realistic closed-loop evaluation in autonomous driving. While 4D Gaussian Splatting (4DGS) offers a promising balance of accuracy and efficiency, existing…
3D Gaussian splatting has surpassed neural radiance field methods in novel view synthesis by achieving lower computational costs and real-time high-quality rendering. Although it produces a high-quality rendering with a lot of input views,…
Generating diverse and high-quality 3D assets automatically poses a fundamental yet challenging task in 3D computer vision. Despite extensive efforts in 3D generation, existing optimization-based approaches struggle to produce large-scale…
Surface reconstruction has been widely studied in computer vision and graphics. However, existing surface reconstruction works struggle to recover accurate scene geometry when the input views are extremely sparse. To address this issue, we…
Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…
We propose DrivingForward, a feed-forward Gaussian Splatting model that reconstructs driving scenes from flexible surround-view input. Driving scene images from vehicle-mounted cameras are typically sparse, with limited overlap, and the…
Multi-view 3D reconstruction has achieved remarkable progress with the advent of feed-forward 3D reconstruction models. However, these models are typically trained and evaluated under ideal, degradation-free imaging conditions, whereas…
3D Gaussian Splatting (3DGS) has recently emerged as a powerful paradigm for photorealistic view synthesis, representing scenes with spatially distributed Gaussian primitives. While highly effective for rendering, achieving accurate and…
Radiance field representations have recently been explored in the latent space of VAEs that are commonly used by diffusion models. This direction offers efficient rendering and seamless integration with diffusion-based pipelines. However,…
Recent prominence in 3D Gaussian Splatting (3DGS) has enabled real-time rendering while maintaining high-fidelity novel view synthesis. However, 3DGS resorts to the Gaussian function that is low-pass by nature and is restricted in…
In this paper, we explore the existing challenges in 3D artistic scene generation by introducing ART3D, a novel framework that combines diffusion models and 3D Gaussian splatting techniques. Our method effectively bridges the gap between…
3D Gaussian Splatting (3DGS) has recently unlocked real-time, high-fidelity novel view synthesis by representing scenes using explicit 3D primitives. However, traditional methods often require millions of Gaussians to capture complex…
Reconstructing high-fidelity underwater scenes remains a challenging task due to light absorption, scattering, and limited visibility inherent in aquatic environments. This paper presents an enhanced Gaussian Splatting-based framework that…
We propose a novel 3D deepfake generation framework based on 3D Gaussian Splatting that enables realistic, identity-preserving face swapping and reenactment in a fully controllable 3D space. Compared to conventional 2D deepfake approaches…