Related papers: Towards Full-to-Empty Room Generation with Structu…

Text-to-image models are showcasing the impressive ability to create high-quality and diverse generative images. Nevertheless, the transition from freehand sketches to complex scene images remains challenging using diffusion models. In this…

We propose a new paradigm to automatically generate training data with accurate labels at scale using the text-to-image synthesis frameworks (e.g., DALL-E, Stable Diffusion, etc.). The proposed approach1 decouples training data generation…

Blur detection aims at segmenting the blurred areas of a given image. Recent deep learning-based methods approach this problem by learning an end-to-end mapping between the blurred input and a binary mask representing the localization of…

Generating semantic layout from scene graph is a crucial intermediate task connecting text to image. We present a conceptually simple, flexible and general framework using sequence to sequence (seq-to-seq) learning for this task. The…

Driving scene parsing is critical for autonomous vehicles to operate reliably in complex real-world traffic environments. To reduce the reliance on costly pixel-level annotations, synthetic datasets with automatically generated labels have…

Semantic segmentation methods have achieved outstanding performance thanks to deep learning. Nevertheless, when such algorithms are deployed to new contexts not seen during training, it is necessary to collect and label scene-specific data…

The increasing demand for autonomous machines in construction environments necessitates the development of robust object detection algorithms that can perform effectively across various weather and environmental conditions. This paper…

Learning to reliably perceive and understand the scene is an integral enabler for robots to operate in the real-world. This problem is inherently challenging due to the multitude of object types as well as appearance changes caused by…

Monocular Semantic Scene Completion (SSC) aims to reconstruct complete 3D semantic scenes from a single RGB image, offering a cost-effective solution for autonomous driving and robotics. However, the inherently imbalanced nature of voxel…

With the recent growth of urban mapping and autonomous driving efforts, there has been an explosion of raw 3D data collected from terrestrial platforms with lidar scanners and color cameras. However, due to high labeling costs, ground-truth…

Modern scene reconstruction methods are able to accurately recover 3D surfaces that are visible in one or more images. However, this leads to incomplete reconstructions, missing all occluded surfaces. While much progress has been made on…

Existing text-to-image diffusion models struggle to synthesize realistic images given dense captions, where each text prompt provides a detailed description for a specific image region. To address this, we propose DenseDiffusion, a…

MonoScene proposes a 3D Semantic Scene Completion (SSC) framework, where the dense geometry and semantics of a scene are inferred from a single monocular RGB image. Different from the SSC literature, relying on 2.5 or 3D input, we solve the…

Grounding textual phrases in visual content is a meaningful yet challenging problem with various potential applications such as image-text inference or text-driven multimedia interaction. Most of the current existing methods adopt the…

Traditional 3D scene understanding approaches rely on labeled 3D datasets to train a model for a single task with supervision. We propose OpenScene, an alternative approach where a model predicts dense features for 3D scene points that are…

Real-world image super-resolution is particularly challenging for diffusion models because real degradations are complex, heterogeneous, and rarely modeled explicitly. We propose a degradation-aware and structure-preserving diffusion…

In this paper, we address the task of semantic-guided scene generation. One open challenge in scene generation is the difficulty of the generation of small objects and detailed local texture, which has been widely observed in global…

Synthesizing normal-light novel views from low-light multiview images is an important yet challenging task, given the low visibility and high ISO noise present in the input images. Existing low-light enhancement methods often struggle to…

Low level image restoration is an integral component of modern artificial intelligence (AI) driven camera pipelines. Most of these frameworks are based on deep neural networks which present a massive computational overhead on resource…

We propose a systematic learning-based approach to the generation of massive quantities of synthetic 3D scenes and arbitrary numbers of photorealistic 2D images thereof, with associated ground truth information, for the purposes of…