Related papers: Genie Sim PanoRecon: Fast Immersive Scene Generati…

Reconstructing complete and interactive 3D scenes remains a fundamental challenge in computer vision and robotics, particularly due to persistent object occlusions and limited sensor coverage. Multiview observations from a single scene scan…

Understanding geometric, semantic, and instance information in 3D scenes from sequential video data is essential for applications in robotics and augmented reality. However, existing Simultaneous Localization and Mapping (SLAM) methods…

Differentiable rendering techniques have recently shown promising results for free-viewpoint video synthesis of characters. However, such methods, either Gaussian Splatting or neural implicit rendering, typically necessitate per-subject…

Sand painting is a process-driven art where visual appearance emerges from granular accumulation. Given a single image, reconstructing a plausible sand painting process requires modeling coherent stroke structures and material-dependent…

Generating high-quality, textured 3D scenes from a single image remains a fundamental challenge in vision and graphics. Recent image-to-3D generators recover reasonable geometry from single views, but their object-centric training limits…

Generating synthetic images is a useful method for cheaply obtaining labeled data for training computer vision models. However, obtaining accurate 3D models of relevant objects is necessary, and the resulting images often have a gap in…

We present Splat-SAP, a feed-forward approach to render novel views of human-centered scenes from binocular cameras with large sparsity. Gaussian Splatting has shown its promising potential in rendering tasks, but it typically necessitates…

We introduce a fully automatic pipeline for dynamic scene reconstruction from casually captured monocular RGB videos. Rather than designing a new scene representation, we enhance the priors that drive Dynamic Gaussian Splatting. Video…

Synthetic 3D scenes are essential for developing Physical AI and generative models. Existing procedural generation methods often have low output throughput, creating a significant bottleneck in scaling up dataset creation. In this work, we…

Generative models have shown substantial impact across multiple domains, their potential for scene synthesis remains underexplored in robotics. This gap is more evident in drone simulators, where simulation environments still rely heavily…

Photorealistic 4D reconstruction of street scenes is essential for developing real-world simulators in autonomous driving. However, most existing methods perform this task offline and rely on time-consuming iterative processes, limiting…

3D city generation with NeRF-based methods shows promising generation results but is computationally inefficient. Recently 3D Gaussian Splatting (3D-GS) has emerged as a highly efficient alternative for object-level 3D generation. However,…

Single-image 3D scene reconstruction presents significant challenges due to its inherently ill-posed nature and limited input constraints. Recent advances have explored two promising directions: multiview generative models that train on 3D…

3D Gaussian Splatting (3DGS) demonstrates unparalleled superior performance in 3D scene reconstruction. However, 3DGS heavily relies on the sharp images. Fulfilling this requirement can be challenging in real-world scenarios especially when…

Recent advances in text-to-3D creation integrate the potent prior of Diffusion Models from text-to-image generation into 3D domain. Nevertheless, generating 3D scenes with multiple objects remains challenging. Therefore, we present…

Recent advances in driving-scene generation and reconstruction have demonstrated significant potential for enhancing autonomous driving systems by producing scalable and controllable training data. Existing generation methods primarily…

There are two prevalent ways to constructing 3D scenes: procedural generation and 2D lifting. Among them, panorama-based 2D lifting has emerged as a promising technique, leveraging powerful 2D generative priors to produce immersive,…

Sparse RGBD scene completion is a challenging task especially when considering consistent textures and geometries throughout the entire scene. Different from existing solutions that rely on human-designed text prompts or predefined camera…

We present a dense simultaneous localization and mapping (SLAM) method that uses 3D Gaussians as a scene representation. Our approach enables interactive-time reconstruction and photo-realistic rendering from real-world single-camera RGBD…

3D scene reconstruction is essential for applications in virtual reality, robotics, and autonomous driving, enabling machines to understand and interact with complex environments. Traditional 3D Gaussian Splatting techniques rely on images…