Search Results for author:
Found 20 papers, 4 papers with code
RGB2Point: 3D Point Cloud Generation from Single RGB Images
RGB2Point takes an input image of an object and generates a dense 3D point cloud.
Tree-D Fusion: Simulation-Ready Tree Dataset from Single Images with Diffusion Priors
We introduce Tree D-fusion, featuring the first collection of 600, 000 environmentally aware, 3D simulation-ready tree models generated through Diffusion priors.
LAESI: Leaf Area Estimation with Synthetic Imagery
We introduce LAESI, a Synthetic Leaf Dataset of 100, 000 synthetic leaf images on millimeter paper, each with semantic masks and surface area labels.
SfmCAD: Unsupervised CAD Reconstruction by Learning Sketch-based Feature Modeling Operations
This paper introduces SfmCAD a novel unsupervised network that reconstructs 3D shapes by learning the Sketch-based Feature Modeling operations commonly used in modern CAD workflows.
Dr. Bokeh: DiffeRentiable Occlusion-aware Bokeh Rendering
Dr. Bokeh then takes the layered representation and user-defined lens parameters to render photo-realistic lens blur based on the novel occlusion-aware bokeh rendering method.
SVDTree: Semantic Voxel Diffusion for Single Image Tree Reconstruction
We cast the 3D information inference problem to a semantic voxel diffusion process which converts an input image of a tree to a novel Semantic Voxel Structure (SVS) in 3D space.
DL3DV-10K: A Large-Scale Scene Dataset for Deep Learning-based 3D Vision
We have witnessed significant progress in deep learning-based 3D vision, ranging from neural radiance field (NeRF) based 3D representation learning to applications in novel view synthesis (NVS).
DeepTree: Modeling Trees with Situated Latents
We use a neural network pipeline to train a situated latent space that allows us to locally predict branch growth only based on a single node in the branch graph of a tree model.
StyleDEM: a Versatile Model for Authoring Terrains
We introduce StyleDEM, a new generative adversarial network method for terrain synthesis and authoring, with a versatile toolbox of authoring methods with style.
SnakeVoxFormer: Transformer-based Single Image\\Voxel Reconstruction with Run Length Encoding
The key novelty of our approach is in using the run-length encoding that traverses (like a snake) the voxel space and encodes wide spatial differences into a 1D structure that is suitable for transformer encoding.
PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing
To compensate for the lack of geometry in 2D Image compositing, recent deep learning-based approaches introduced a pixel height representation to generate soft shadows and reflections.
Tree Instance Segmentation With Temporal Contour Graph
We present a novel approach to perform instance segmentation, and counting, for densely packed self-similar trees using a top-view RGB image sequence.
Controllable Shadow Generation Using Pixel Height Maps
It can be used to calculate hard shadows in a 2D image based on the projective geometry, providing precise control of the shadows' direction and shape.
Co-design of Embodied Neural Intelligence via Constrained Evolution
The agent is then randomly modified within the allowed ranges creating a new generation of several hundred agents.
Procedural Urban Forestry
The placement of vegetation plays a central role in the realism of virtual scenes.
SSN: Soft Shadow Network for Image Compositing
We demonstrate that our model produces realistic soft shadows in real-time.
Efficient Project Gradient Descent for Ensemble Adversarial Attack
Consider $l_2$ norms attacks, Project Gradient Descent (PGD) and the Carlini and Wagner (C\&W) attacks are the two main methods, where PGD control max perturbation for adversarial examples while C\&W approach treats perturbation as a regularization term optimized it with loss function together.
Understanding and Exploiting Object Interaction Landscapes
We introduce a new general representation for proximal interactions among physical objects that is agnostic to the type of objects or interaction involved.
Procedural Editing of 3D Building Point Clouds
Thanks to the recent advances in computational photography and remote sensing, point clouds of buildings are becoming increasingly available, yet their processing poses various challenges.
