Related papers: Smartphone scene generator for efficient character…
Film set design plays a pivotal role in cinematic storytelling and shaping the visual atmosphere. However, the traditional process depends on expert-driven manual modeling, which is labor-intensive and time-consuming. To address this issue,…
Text-driven 3D scene generation holds promise for a wide range of applications, from virtual prototyping to AR/VR and simulation. However, existing methods are often constrained to single-object generation, require domain-specific training,…
Image recognition/classification is a widely studied problem, but its reverse problem, image generation, has drawn much less attention until recently. But the vast majority of current methods for image generation require training/retraining…
Autonomous driving promises safer roads, reduced congestion, and improved mobility, yet validating these systems across diverse conditions remains a major challenge. Real-world testing is expensive, time-consuming, and sometimes unsafe,…
Object detection is an algorithm that recognizes and locates the objects in the image and has a wide range of applications in the visual understanding of complex urban scenes. Existing object detection benchmarks mainly focus on a single…
3D scene generation has garnered growing attention in recent years and has made significant progress. Generating 4D cities is more challenging than 3D scenes due to the presence of structurally complex, visually diverse objects like…
Generating 3D scenes from natural language holds great promise for applications in gaming, film, and design. However, existing methods struggle with automation, 3D consistency, and fine-grained control. We present DreamScene, an end-to-end…
Reconstructing photo-realistic large-scale scenes from images, for example at city scale, is a long-standing problem in computer graphics. Neural rendering is an emerging technique that enables photo-realistic image synthesis from…
We introduce a method for the generation of images from an input scene graph. The method separates between a layout embedding and an appearance embedding. The dual embedding leads to generated images that better match the scene graph, have…
Scene Graph Generation (SGG) unifies object localization and visual relationship reasoning by predicting boxes and subject-predicate-object triples. Yet most pipelines treat SGG as a one-shot, deterministic classification problem rather…
Implementing color constancy as a pre-processing step in contemporary digital cameras is of significant importance as it removes the influence of scene illumination on object colors. Several benchmark color constancy datasets have been…
The use of coarse-grained layouts for controllable synthesis of complex scene images via deep generative models has recently gained popularity. However, results of current approaches still fall short of their promise of high-resolution…
The requirement of large amounts of annotated images has become one grand challenge while training deep neural network models for various visual detection and recognition tasks. This paper presents a novel image synthesis technique that…
This position paper argues for the use of \emph{structured generative models} (SGMs) for the understanding of static scenes. This requires the reconstruction of a 3D scene from an input image (or a set of multi-view images), whereby the…
We aim to generate fine-grained 3D geometry from large-scale sparse LiDAR scans, abundantly captured by autonomous vehicles (AV). Contrary to prior work on AV scene completion, we aim to extrapolate fine geometry from unlabeled and beyond…
Learning-based methods for training embodied agents typically require a large number of high-quality scenes that contain realistic layouts and support meaningful interactions. However, current simulators for Embodied AI (EAI) challenges…
We present a method that leverages the complementarity of event cameras and standard cameras to track visual features with low-latency. Event cameras are novel sensors that output pixel-level brightness changes, called "events". They offer…
Synthetic data used for scene text detection and recognition tasks have proven effective. However, there are still two problems: First, the color schemes used for text coloring in the existing methods are relatively fixed color key-value…
The task of generating natural images from 3D scenes has been a long standing goal in computer graphics. On the other hand, recent developments in deep neural networks allow for trainable models that can produce natural-looking images with…
Recent advances in diffusion models have revolutionized 2D and 3D content creation, yet generating photorealistic dynamic 4D scenes remains a significant challenge. Existing dynamic 4D generation methods typically rely on distilling…