Related papers: SceneTransporter: Optimal Transport-Guided Composi…
We introduce Scenario Dreamer, a fully data-driven generative simulator for autonomous vehicle planning that generates both the initial traffic scene - comprising a lane graph and agent bounding boxes - and closed-loop agent behaviours.…
Optimal Transport has recently gained interest in machine learning for applications ranging from domain adaptation, sentence similarities to deep learning. Yet, its ability to capture frequently occurring structure beyond the "ground…
Existing generative approaches for guided image synthesis of multi-object scenes typically rely on 2D controls in the image or text space. As a result, these methods struggle to maintain and respect consistent three-dimensional geometric…
We propose a method for generating fly-through videos of a scene, from a single image and a given camera trajectory. We build upon an image-to-video latent diffusion model. We condition its UNet denoiser on the camera trajectory, using four…
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…
Autonomous vehicles operate in highly dynamic environments necessitating an accurate assessment of which aspects of a scene are moving and where they are moving to. A popular approach to 3D motion estimation, termed scene flow, is to employ…
Simulation forms the backbone of modern self-driving development. Simulators help develop, test, and improve driving systems without putting humans, vehicles, or their environment at risk. However, simulators face a major challenge: They…
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…
Recent advances in diffusion transformers (DiTs) have set new standards in image generation, yet remain impractical for on-device deployment due to their high computational and memory costs. In this work, we present an efficient DiT…
Scene segmentation is widely used in the field of autonomous driving for environment perception, and semantic scene segmentation (3S) has received a great deal of attention due to the richness of the semantic information it contains. It…
With the widespread use of virtual reality applications, 3D scene generation has become a new challenging research frontier. 3D scenes have highly complex structures and need to ensure that the output is dense, coherent, and contains all…
The whole is greater than the sum of its parts-even in 3D-text contrastive learning. We introduce SceneForge, a novel framework that enhances contrastive alignment between 3D point clouds and text through structured multi-object scene…
Single-image 3D generation lies at the core of vision-to-graphics models in the real world. However, it remains a fundamental challenge to achieve reliable generalization across diverse semantic categories and highly variable structural…
Generating 3D worlds from text is a highly anticipated goal in computer vision. Existing works are limited by the degree of exploration they allow inside of a scene, i.e., produce streched-out and noisy artifacts when moving beyond central…
Generating immersive 3D scenes from texts is a core task in computer vision, crucial for applications in virtual reality and game development. Despite the promise of leveraging 2D diffusion priors, existing methods suffer from spatial…
Dataset distillation seeks to synthesize a compact distilled dataset, enabling models trained on it to achieve performance comparable to models trained on the full dataset. Recent methods for large-scale datasets focus on matching global…
The recent success of transformer-based image generative models in object-centric learning highlights the importance of powerful image generators for handling complex scenes. However, despite the high expressiveness of diffusion models in…
Achieving highly accurate and real-time 3D occupancy prediction from cameras is a critical requirement for the safe and practical deployment of autonomous vehicles. While this shift to sparse 3D representations solves the encoding…
Videos convey richer information than images or text, capturing both spatial and temporal dynamics. However, most existing video customization methods rely on reference images or task-specific temporal priors, failing to fully exploit the…
Despite remarkable achievements in video synthesis, achieving granular control over complex dynamics, such as nuanced movement among multiple interacting objects, still presents a significant hurdle for dynamic world modeling, compounded by…