372 citations · 1k across the 31 of their papers we have counts for
17 papers · 1 filter
GSComplete: Gaussian Splat Completion with 2D Diffusion Priors
Elias Brugger, Philipp Erler, Stefan Ohrhallinger +1
Gaussian splats provide a fast, high-fidelity representation for 3D objects but are often constructed from incomplete input data in practice, leaving missing regions. Existing comp…
PhotoMat: A Material Generator Learned from Single Flash Photos
Xilong Zhou, Miloš Hašan, Valentin Deschaintre +4
Authoring high-quality digital materials is key to realism in 3D rendering. Previous generative models for materials have been trained exclusively on synthetic data; such data is l…
Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly
Xianghao Xu, Paul Guerrero, Matthew Fisher +2
Representing a 3D shape with a set of primitives can aid perception of structure, improve robotic object manipulation, and enable editing, stylization, and compression of 3D shapes…
3D-LDM: Neural Implicit 3D Shape Generation with Latent Diffusion Models
Gimin Nam, Mariem Khlifi, Andrew Rodriguez +3
Diffusion models have shown great promise for image generation, beating GANs in terms of generation diversity, with comparable image quality. However, their application to 3D shape…
RenderDiffusion: Image Diffusion for 3D Reconstruction, Inpainting and Generation
Titas Anciukevičius, Zexiang Xu, Matthew Fisher +4
Diffusion models currently achieve state-of-the-art performance for both conditional and unconditional image generation. However, so far, image diffusion models do not support task…
Search for Concepts: Discovering Visual Concepts Using Direct Optimization
Pradyumna Reddy, Paul Guerrero, Niloy J. Mitra
Finding an unsupervised decomposition of an image into individual objects is a key step to leverage compositionality and to perform symbolic reasoning. Traditionally, this problem…
NeuForm: Adaptive Overfitting for Neural Shape Editing
Connor Z. Lin, Niloy J. Mitra, Gordon Wetzstein +2
Neural representations are popular for representing shapes, as they can be learned form sensor data and used for data cleanup, model completion, shape editing, and shape synthesis.…
COFS: Controllable Furniture layout Synthesis
Wamiq Reyaz Para, Paul Guerrero, Niloy Mitra +1
Scalable generation of furniture layouts is essential for many applications in virtual reality, augmented reality, game development and synthetic data generation. Many existing met…
Neural Convolutional Surfaces
Luca Morreale, Noam Aigerman, Paul Guerrero +2
This work is concerned with a representation of shapes that disentangles fine, local and possibly repeating geometry, from global, coarse structures. Achieving such disentanglement…
Differentiable Surface Triangulation
Marie-Julie Rakotosaona, Noam Aigerman, Niloy Mitra +2
Triangle meshes remain the most popular data representation for surface geometry. This ubiquitous representation is essentially a hybrid one that decouples continuous vertex locati…
Learning Delaunay Surface Elements for Mesh Reconstruction
Marie-Julie Rakotosaona, Paul Guerrero, Noam Aigerman +2
We present a method for reconstructing triangle meshes from point clouds. Existing learning-based methods for mesh reconstruction mostly generate triangles individually, making it…
Generative Layout Modeling using Constraint Graphs
Wamiq Para, Paul Guerrero, Tom Kelly +2
We propose a new generative model for layout generation. We generate layouts in three steps. First, we generate the layout elements as nodes in a layout graph. Second, we compute c…
Discovering Pattern Structure Using Differentiable Compositing
Pradyumna Reddy, Paul Guerrero, Matt Fisher +2
Patterns, which are collections of elements arranged in regular or near-regular arrangements, are an important graphic art form and widely used due to their elegant simplicity and…
Pix2Surf: Learning Parametric 3D Surface Models of Objects from Images
Jiahui Lei, Srinath Sridhar, Paul Guerrero +3
We investigate the problem of learning to generate 3D parametric surface representations for novel object instances, as seen from one or more views. Previous work on learning shape…
Points2Surf: Learning Implicit Surfaces from Point Cloud Patches
Philipp Erler, Paul Guerrero, Stefan Ohrhallinger +2
A key step in any scanning-based asset creation workflow is to convert unordered point clouds to a surface. Classical methods (e.g., Poisson reconstruction) start to degrade in the…
StructEdit: Learning Structural Shape Variations
Kaichun Mo, Paul Guerrero, Li Yi +4
Learning to encode differences in the geometry and (topological) structure of the shapes of ordinary objects is key to generating semantically plausible variations of a given shape…
DepthCut: Improved Depth Edge Estimation Using Multiple Unreliable Channels
Paul Guerrero, Holger Winnemöller, Wilmot Li +1
In the context of scene understanding, a variety of methods exists to estimate different information channels from mono or stereo images, including disparity, depth, and normals. A…