Related papers: Pixal3D: Pixel-Aligned 3D Generation from Images

Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to…

Traditional image-to-3D models often struggle with scenes containing multiple objects due to biases and occlusion complexities. To address this challenge, we present REPARO, a novel approach for compositional 3D asset generation from single…

3D generation methods have shown visually compelling results powered by diffusion image priors. However, they often fail to produce realistic geometric details, resulting in overly smooth surfaces or geometric details inaccurately baked in…

Recently, generating 3D assets with the control of condition images has achieved impressive quality. However, existing 3D generation methods are limited to handling a single control objective and lack the ability to utilize multiple images…

Object recognition has seen significant progress in the image domain, with focus primarily on 2D perception. We propose to leverage existing large-scale datasets of 3D models to understand the underlying 3D structure of objects seen in an…

Recent years have seen an explosion of work and interest in text-to-3D shape generation. Much of the progress is driven by advances in 3D representations, large-scale pretraining and representation learning for text and image data enabling…

We present Seed3D 2.0, an advanced 3D content generation system built on Seed3D 1.0, with substantial improvements across generation fidelity, simulation-ready capabilities, and application coverage. For geometry, a coarse-to-fine two-stage…

We propose a probabilistic shape completion method extended to the continuous geometry of large-scale 3D scenes. Real-world scans of 3D scenes suffer from a considerable amount of missing data cluttered with unsegmented objects. The problem…

Recently single-view 3D generation via Gaussian splatting has emerged and developed quickly. They learn 3D Gaussians from 2D RGB images generated from pre-trained multi-view diffusion (MVD) models, and have shown a promising avenue for 3D…

In this paper, we propose Extend3D, a training-free pipeline for 3D scene generation from a single image, built upon an object-centric 3D generative model. To overcome the limitations of fixed-size latent spaces in object-centric models for…

Envisioning physically plausible outcomes from a single image requires a deep understanding of the world's dynamics. To address this, we introduce PhysGen3D, a novel framework that transforms a single image into an amodal, camera-centric,…

In contrast to the traditional avatar creation pipeline which is a costly process, contemporary generative approaches directly learn the data distribution from photographs. While plenty of works extend unconditional generative models and…

Recent studies on 3D hand reconstruction have demonstrated the effectiveness of synthetic training data to improve estimation performance. However, most methods rely on game engines to synthesize hand images, which often lack diversity in…

Generating 3D models lies at the core of computer graphics and has been the focus of decades of research. With the emergence of advanced neural representations and generative models, the field of 3D content generation is developing rapidly,…

Explorable 3D world generation from a single image or text prompt forms a cornerstone of spatial intelligence. Recent works utilize video model to achieve wide-scope and generalizable 3D world generation. However, existing approaches often…

We introduce a high resolution, 3D-consistent image and shape generation technique which we call StyleSDF. Our method is trained on single-view RGB data only, and stands on the shoulders of StyleGAN2 for image generation, while solving two…

3D-aware GANs aim to synthesize realistic 3D scenes such that they can be rendered in arbitrary perspectives to produce images. Although previous methods produce realistic images, they suffer from unstable training or degenerate solutions…

We present a method of generating high resolution 3D shapes from natural language descriptions. To achieve this goal, we propose two steps that generating low resolution shapes which roughly reflect texts and generating high resolution…

Many robotic tasks involving some form of 3D visual perception greatly benefit from a complete knowledge of the working environment. However, robots often have to tackle unstructured environments and their onboard visual sensors can only…

State-of-the-art 3D-aware generative models rely on coordinate-based MLPs to parameterize 3D radiance fields. While demonstrating impressive results, querying an MLP for every sample along each ray leads to slow rendering. Therefore,…