Related papers: 3D-Adapter: Geometry-Consistent Multi-View Diffusi…

Recent years have witnessed remarkable progress in multi-view diffusion models for 3D content creation. However, there remains a significant gap in image quality and prompt-following ability compared to 2D diffusion models. A critical…

We tackle the problem of text-driven 3D generation from a geometry alignment perspective. Given a set of text prompts, we aim to generate a collection of objects with semantically corresponding parts aligned across them. Recent methods…

Multi-view generation with camera pose control and prompt-based customization are both essential elements for achieving controllable generative models. However, existing multi-view generation models do not support customization with…

Dense 3D reconstruction from continuous image streams requires both accurate geometric aggregation and stable long-term memory management. Recent feed-forward reconstruction frameworks integrate observations through persistent memory…

3D-aware image generation necessitates extensive training data to ensure stable training and mitigate the risk of overfitting. This paper first considers a novel task known as One-shot 3D Generative Domain Adaptation (GDA), aimed at…

As a promising 3D generation technique, multiview diffusion (MVD) has received a lot of attention due to its advantages in terms of generalizability, quality, and efficiency. By finetuning pretrained large image diffusion models with 3D…

This paper introduces a pioneering 3D volumetric encoder designed for text-to-3D generation. To scale up the training data for the diffusion model, a lightweight network is developed to efficiently acquire feature volumes from multi-view…

Recent advancements in image synthesis are fueled by the advent of large-scale diffusion models. Yet, integrating realistic object visualizations seamlessly into new or existing backgrounds without extensive training remains a challenge.…

Unsupervised generation of high-quality multi-view-consistent images and 3D shapes using only collections of single-view 2D photographs has been a long-standing challenge. Existing 3D GANs are either compute-intensive or make approximations…

Recently, text-to-image generation has exhibited remarkable advancements, with the ability to produce visually impressive results. In contrast, text-to-3D generation has not yet reached a comparable level of quality. Existing methods…

Lifting 2D diffusion for 3D generation is a challenging problem due to the lack of geometric prior and the complex entanglement of materials and lighting in natural images. Existing methods have shown promise by first creating the geometry…

Video generation models have made significant progress in generating realistic content, enabling applications in simulation, gaming, and film making. However, current generated videos still contain visual artifacts arising from 3D…

Text-to-3D is an emerging task that allows users to create 3D content with infinite possibilities. Existing works tackle the problem by optimizing a 3D representation with guidance from pre-trained diffusion models. An apparent drawback is…

Real-time free-viewpoint rendering requires balancing multi-camera redundancy with the latency constraints of interactive applications. We address this challenge by combining lightweight geometry with learning and propose 3DTV, a…

Recent advances in 3D generation have been remarkable, with methods such as DreamFusion leveraging large-scale text-to-image diffusion-based models to guide 3D object generation. These methods enable the synthesis of detailed and…

While generative artificial intelligence has advanced significantly across text, image, audio, and video domains, 3D generation remains comparatively underdeveloped due to fundamental challenges such as data scarcity, algorithmic…

We present a novel framework for generating photorealistic 3D human head and subsequently manipulating and reposing them with remarkable flexibility. The proposed approach leverages an implicit function representation of 3D human heads,…

We propose a system that learns to detect objects and infer their 3D poses in RGB-D images. Many existing systems can identify objects and infer 3D poses, but they heavily rely on human labels and 3D annotations. The challenge here is to…

Understanding 3D scenes from multi-view inputs has been proven to alleviate the view discrepancy issue in 3D visual grounding. However, existing methods normally neglect the view cues embedded in the text modality and fail to weigh the…

This paper tackles the problem of generalizable 3D-aware generation from monocular datasets, e.g., ImageNet. The key challenge of this task is learning a robust 3D-aware representation without multi-view or dynamic data, while ensuring…