Related papers: Controllable Shadow Generation with Single-Step Di…

Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. Additionally, 3D scene generation is vital for advancing embodied AI and world models, which depend…

3D data simulation aims to bridge the gap between simulated and real-captured 3D data, which is a fundamental problem for real-world 3D visual tasks. Most 3D data simulation methods inject predefined physical priors but struggle to capture…

Despite recent advancements in neural 3D reconstruction, the dependence on dense multi-view captures restricts their broader applicability. In this work, we propose \textbf{ViewCrafter}, a novel method for synthesizing high-fidelity novel…

Novel view synthesis from a single input image is a challenging task, where the goal is to generate a new view of a scene from a desired camera pose that may be separated by a large motion. The highly uncertain nature of this synthesis task…

Shadows, formed by the occlusion of light, play an essential role in visual perception and directly influence scene understanding, image quality, and visual realism. This paper presents a unified survey and benchmark of deep-learning-based…

Diffusion models have significantly advanced the fields of image, audio, and video generation, but they depend on an iterative sampling process that causes slow generation. To overcome this limitation, we propose consistency models, a new…

Although diffusion-based models can generate high-quality and high-resolution video sequences from textual or image inputs, they lack explicit integration of geometric cues when controlling scene lighting and visual appearance across…

The field of generative models has recently witnessed significant progress, with diffusion models showing remarkable performance in image generation. In light of this success, there is a growing interest in exploring the application of…

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…

As synthetic imagery is used more frequently in training deep models, it is important to understand how different synthesis techniques impact the performance of such models. In this work, we perform a thorough evaluation of the…

Conditional diffusion models have demonstrated impressive performance in image manipulation tasks. The general pipeline involves adding noise to the image and then denoising it. However, this method faces a trade-off problem: adding too…

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…

Semantic scene understanding is crucial for robotics and computer vision applications. In autonomous driving, 3D semantic segmentation plays an important role for enabling safe navigation. Despite significant advances in the field, the…

We target a 3D generative model for general natural scenes that are typically unique and intricate. Lacking the necessary volumes of training data, along with the difficulties of having ad hoc designs in presence of varying scene…

Recent works on text-to-3d generation show that using only 2D diffusion supervision for 3D generation tends to produce results with inconsistent appearances (e.g., faces on the back view) and inaccurate shapes (e.g., animals with extra…

Bokeh rendering simulates the shallow depth-of-field effect in photography, enhancing visual aesthetics and guiding viewer attention to regions of interest. Although recent approaches perform well, rendering controllable bokeh without…

We tackle the problem of generating highly realistic and plausible mirror reflections using diffusion-based generative models. We formulate this problem as an image inpainting task, allowing for more user control over the placement of…

Existing portrait relighting methods struggle with precise control over facial shadows, particularly when faced with challenges such as handling hard shadows from directional light sources or adjusting shadows while remaining in harmony…

Simulation is increasingly being used for generating large labelled datasets in many machine learning problems. Recent methods have focused on adjusting simulator parameters with the goal of maximising accuracy on a validation task, usually…

We present TextureDreamer, a novel image-guided texture synthesis method to transfer relightable textures from a small number of input images (3 to 5) to target 3D shapes across arbitrary categories. Texture creation is a pivotal challenge…