相关论文: PolyOculus: Simultaneous Multi-view Image-based No…

3D Gaussian Splatting has recently emerged as a powerful tool for fast and accurate novel-view synthesis from a set of posed input images. However, like most novel-view synthesis approaches, it relies on accurate camera pose information,…

Structure from motion (SfM) enables us to reconstruct a scene via casual capture from cameras at different viewpoints, and novel view synthesis (NVS) allows us to render a captured scene from a new viewpoint. Both are hard with casual…

Recent improvements to Generative Adversarial Networks (GANs) have made it possible to generate realistic images in high resolution based on natural language descriptions such as image captions. Furthermore, conditional GANs allow us to…

Predicting novel views of a scene from real-world images has always been a challenging task. In this work, we propose a deep convolutional neural network (CNN) which learns to predict novel views of a scene from given collection of images.…

Novel-view synthesis (NVS) can be tackled through different approaches, depending on the general setting: a single source image to a short video sequence, exact or noisy camera pose information, 3D-based information such as point clouds…

In order to operate autonomously, a robot should explore the environment and build a model of each of the surrounding objects. A common approach is to carefully scan the whole workspace. This is time-consuming. It is also often impossible…

Generative reconstruction methods compute the 3D configuration (such as pose and/or geometry) of a shape by optimizing the overlap of the projected 3D shape model with images. Proper handling of occlusions is a big challenge, since the…

Diffusion-based approaches have recently demonstrated strong performance for single-image novel view synthesis by conditioning generative models on geometry inferred from monocular depth estimation. However, in practice, the quality and…

Novel view synthesis requires strong 3D geometric consistency and the ability to generate visually coherent images across diverse viewpoints. While recent camera-controlled video diffusion models show promising results, they often suffer…

We present a method for learning to generate unbounded flythrough videos of natural scenes starting from a single view, where this capability is learned from a collection of single photographs, without requiring camera poses or even…

We present Thinking with Generated Images, a novel paradigm that fundamentally transforms how large multimodal models (LMMs) engage with visual reasoning by enabling them to natively think across text and vision modalities through…

Generative AI is transforming image synthesis, enabling the creation of high-quality, diverse, and photorealistic visuals across industries like design, media, healthcare, and autonomous systems. Advances in techniques such as…

We introduce an approach to enhance the novel view synthesis from images taken from a freely moving camera. The introduced approach focuses on outdoor scenes where recovering accurate geometric scaffold and camera pose is challenging,…

The development of generalizable Novel View Synthesis (NVS) models is critically limited by the scarcity of large-scale training data featuring diverse and precise camera trajectories. While real-world captures are photorealistic, they are…

Novel view synthesis (NVS) is a challenging task requiring systems to generate photorealistic images of scenes from new viewpoints, where both quality and speed are important for applications. Previous image-based rendering (IBR) methods…

Synthesizing photo-realistic visual observations from an ego vehicle's driving trajectory is a critical step towards scalable training of self-driving models. Reconstruction-based methods create 3D scenes from driving logs and synthesize…

Recent advances in image generation have achieved remarkable visual quality, while a fundamental challenge remains: Can image generation be controlled at the element level, enabling intuitive modifications such as adjusting shapes, altering…

While generative modeling on multimodal image-text data has been actively developed with large-scale paired datasets, there have been limited attempts to generate both image and text data by a single model rather than a generation of one…

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…

We present an algorithm for generating novel views at arbitrary viewpoints and any input time step given a monocular video of a dynamic scene. Our work builds upon recent advances in neural implicit representation and uses continuous and…