Related papers: Appearance-Driven Automatic 3D Model Simplificatio…
Multiview diffusion models have rapidly emerged as a powerful tool for content creation with spatial consistency across viewpoints, offering rich visual realism without requiring explicit geometry and appearance representation. However,…
While deep learning methods have achieved impressive success in many vision benchmarks, it remains difficult to understand and explain the representations and decisions of these models. Though vision models are typically trained on 2D…
Recent years have seen the development of mature solutions for reconstructing deformable surfaces from a single image, provided that they are relatively well-textured. By contrast, recovering the 3D shape of texture-less surfaces remains an…
Understanding 3D scenes requires flexible combinations of visual reasoning tasks, including depth estimation, novel view synthesis, and object manipulation, all of which are essential for perception and interaction. Existing approaches have…
We present neural architectures that disentangle RGB-D images into objects' shapes and styles and a map of the background scene, and explore their applications for few-shot 3D object detection and few-shot concept classification. Our…
There has recently been great interest in neural rendering methods. Some approaches use 3D geometry reconstructed with Multi-View Stereo (MVS) but cannot recover from the errors of this process, while others directly learn a volumetric…
Generating 3D scenes from human motion sequences supports numerous applications, including virtual reality and architectural design. However, previous auto-regression-based human-aware 3D scene generation methods have struggled to…
We present a method for the digital fabrication of surfaces whose appearance varies based on viewing direction. The surfaces are constructed from a mesh of bars arranged in a self-occluding colored heightfield that creates the desired…
Triangles are everywhere in the virtual world. The surface of nearly every graphical object is saved as a triangular mesh on a computer. Light effects and movements of virtual objects are computed on the basis of triangulations. Besides…
Three-dimensional (3D) object reconstruction based on differentiable rendering (DR) is an active research topic in computer vision. DR-based methods minimize the difference between the rendered and target images by optimizing both the shape…
Promising performance has been achieved for visual perception on the point cloud. However, the current methods typically rely on labour-extensive annotations on the scene scans. In this paper, we explore how synthetic models alleviate the…
Highly expressive models such as deep neural networks (DNNs) have been widely applied to various applications. However, recent studies show that DNNs are vulnerable to adversarial examples, which are carefully crafted inputs aiming to…
Novel view synthesis has shown rapid progress recently, with methods capable of producing increasingly photorealistic results. 3D Gaussian Splatting has emerged as a promising method, producing high-quality renderings of scenes and enabling…
3D face reconstruction (3DFR) algorithms are based on specific assumptions tailored to the limits and characteristics of the different application scenarios. In this study, we investigate how multiple state-of-the-art 3DFR algorithms can be…
We present a user-friendly image editing system that supports a drag-and-drop object insertion (where the user merely drags objects into the image, and the system automatically places them in 3D and relights them appropriately),…
We present a differentiable representation, DMesh, for general 3D triangular meshes. DMesh considers both the geometry and connectivity information of a mesh. In our design, we first get a set of convex tetrahedra that compactly tessellates…
3D content creation via text-driven stylization has played a fundamental challenge to multimedia and graphics community. Recent advances of cross-modal foundation models (e.g., CLIP) have made this problem feasible. Those approaches…
This paper introduces a method for simplifying textured surface triangle meshes in the wild while maintaining high visual quality. While previous methods achieve excellent results on manifold meshes by using the quadric error metric, they…
Class-agnostic 3D instance segmentation tackles the challenging task of segmenting all object instances, including previously unseen ones, without semantic class reliance. Current methods struggle with generalization due to the scarce…
We present a differentiable volume rendering solution that provides differentiability of all continuous parameters of the volume rendering process. This differentiable renderer is used to steer the parameters towards a setting with an…