Related papers: HyperColor: A HyperNetwork Approach for Synthesizi…

We introduce a recipe for generating immersive 3D worlds from a single image by framing the task as an in-context learning problem for 2D inpainting models. This approach requires minimal training and uses existing generative models. Our…

We present a deep reinforcement learning method of progressive view inpainting for colored semantic point cloud scene completion under volume guidance, achieving high-quality scene reconstruction from only a single RGB-D image with severe…

We propose a method for scene-level sketch-to-photo synthesis with text guidance. Although object-level sketch-to-photo synthesis has been widely studied, whole-scene synthesis is still challenging without reference photos that adequately…

Scene understanding is a prerequisite to many high level tasks for any automated intelligent machine operating in real world environments. Recent attempts with supervised learning have shown promise in this direction but also highlighted…

One of the biggest challenges in machine learning is data collection. Training data is an important part since it determines how the model will behave. In object classification, capturing a large number of images per object and in different…

3D multi object generative models allow us to synthesize a large range of novel 3D multi object scenes and also identify objects, shapes, layouts and their positions. But multi object scenes are difficult to create because of the dataset…

While deep neural networks have led to human-level performance on computer vision tasks, they have yet to demonstrate similar gains for holistic scene understanding. In particular, 3D context has been shown to be an extremely important cue…

We tackle a new problem of semantic view synthesis -- generating free-viewpoint rendering of a synthesized scene using a semantic label map as input. We build upon recent advances in semantic image synthesis and view synthesis for handling…

Advances in Generative AI tools have allowed designers to manipulate existing 3D models using text or image-based prompts, enabling creators to explore different design goals. Photochromic color-changing systems, on the other hand, allow…

The manual annotation for large-scale point clouds costs a lot of time and is usually unavailable in harsh real-world scenarios. Inspired by the great success of the pre-training and fine-tuning paradigm in both vision and language tasks,…

Transferring the style from one image onto another is a popular and widely studied task in computer vision. Yet, style transfer in the 3D setting remains a largely unexplored problem. To our knowledge, we propose the first learning-based…

Image synthesis has attracted emerging research interests in academic and industry communities. Deep learning technologies especially the generative models greatly inspired controllable image synthesis approaches and applications, which aim…

Recent advances in text-driven 3D scene editing and stylization, which leverage the powerful capabilities of 2D generative models, have demonstrated promising outcomes. However, challenges remain in ensuring high-quality stylization and…

Generating high-quality textures for 3D scenes is crucial for applications in interior design, gaming, and augmented/virtual reality (AR/VR). Although recent advancements in 3D generative models have enhanced content creation, significant…

In the current deep learning paradigm, the amount and quality of training data are as critical as the network architecture and its training details. However, collecting, processing, and annotating real data at scale is difficult, expensive,…

Many deep learning based 3D face reconstruction methods have been proposed recently, however, few of them have applications in games. Current game character customization systems either require players to manually adjust considerable face…

Designing 3D scenes is traditionally a challenging task that demands both artistic expertise and proficiency with complex software. Recent advances in text-to-3D generation have greatly simplified this process by letting users create scenes…

Training models to high-end performance requires availability of large labeled datasets, which are expensive to get. The goal of our work is to automatically synthesize labeled datasets that are relevant for a downstream task. We propose…

Continual learning refers to the ability of humans and animals to incrementally learn over time in a given environment. Trying to simulate this learning process in machines is a challenging task, also due to the inherent difficulty in…

Diffusion models have shown great promise in synthesizing visually appealing images. However, it remains challenging to condition the synthesis at a fine-grained level, for instance, synthesizing image pixels following some generic color…