Related papers: Text To 3D Object Generation For Scalable Room Ass…
Semantic understanding of scenes in three-dimensional space (3D) is a quintessential part of robotics oriented applications such as autonomous driving as it provides geometric cues such as size, orientation and true distance of separation…
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…
Methods that synthesize indoor 3D scenes from text prompts have wide-ranging applications in film production, interior design, video games, virtual reality, and synthetic data generation for training embodied agents. Existing approaches…
The performance of supervised deep learning algorithms depends significantly on the scale, quality and diversity of the data used for their training. Collecting and manually annotating large amount of data can be both time-consuming and…
Large-scale robot datasets have facilitated the learning of a wide range of robot manipulation skills, but these datasets remain difficult to collect and scale further, owing to the intractable amount of human time, effort, and cost…
Exploiting synthetic data to learn deep models has attracted increasing attention in recent years. However, the intrinsic domain difference between synthetic and real images usually causes a significant performance drop when applying the…
The recent availability and adaptability of text-to-image models has sparked a new era in many related domains that benefit from the learned text priors as well as high-quality and fast generation capabilities, one of which is texture…
We present MAV3D (Make-A-Video3D), a method for generating three-dimensional dynamic scenes from text descriptions. Our approach uses a 4D dynamic Neural Radiance Field (NeRF), which is optimized for scene appearance, density, and motion…
Recently, the use of synthetic datasets based on game engines has been shown to improve the performance of several tasks in computer vision. However, these datasets are typically only appropriate for the specific domains depicted in…
We present DiffuScene for indoor 3D scene synthesis based on a novel scene configuration denoising diffusion model. It generates 3D instance properties stored in an unordered object set and retrieves the most similar geometry for each…
3D content generation has recently attracted significant research interest, driven by its critical applications in VR/AR and embodied AI. In this work, we tackle the challenging task of synthesizing multiple 3D assets within a single scene…
The significant progress on Generative Adversarial Networks (GANs) have made it possible to generate surprisingly realistic images for single object based on natural language descriptions. However, controlled generation of images for…
Text-to-3D generation has achieved remarkable success via large-scale text-to-image diffusion models. Nevertheless, there is no paradigm for scaling up the methodology to urban scale. Urban scenes, characterized by numerous elements,…
We address the task of indoor scene generation by generating a sequence of objects, along with their locations and orientations conditioned on a room layout. Large-scale indoor scene datasets allow us to extract patterns from user-designed…
Recently, diffusion-based image generation methods are credited for their remarkable text-to-image generation capabilities, while still facing challenges in accurately generating multilingual scene text images. To tackle this problem, we…
This paper proposes a novel framework for generating lingual descriptions of indoor scenes. Whereas substantial efforts have been made to tackle this problem, previous approaches focusing primarily on generating a single sentence for each…
The crux of text-to-image synthesis stems from the difficulty of preserving the cross-modality semantic consistency between the input text and the synthesized image. Typical methods, which seek to model the text-to-image mapping directly,…
Recent advances in deep learning have brought significant progress in visual grounding tasks such as language-guided video object segmentation. However, collecting large datasets for these tasks is expensive in terms of annotation time,…
Image generation today can produce somewhat realistic images from text prompts. However, if one asks the generator to synthesize a specific camera setting such as creating different fields of view using a 24mm lens versus a 70mm lens, the…
Text-driven 3D indoor scene generation is useful for gaming, the film industry, and AR/VR applications. However, existing methods cannot faithfully capture the room layout, nor do they allow flexible editing of individual objects in the…