Computer Graphics Papers
@Animation
Followers
2K
Following
0
Media
0
Statuses
4K
New Computer Graphics submissions https://t.co/jxQoqsUZrX (not affiliated with https://t.co/jxQoqsUZrX)
Joined August 2009
MaskedManipulator: Versatile Whole-Body Manipulation.
arxiv.org
We tackle the challenges of synthesizing versatile, physically simulated human motions for full-body object manipulation. Unlike prior methods that are focused on detailed motion tracking,...
0
0
0
ShapeWords: Guiding Text-to-Image Synthesis with 3D Shape-Aware Prompts.
arxiv.org
We introduce ShapeWords, an approach for synthesizing images based on 3D shape guidance and text prompts. ShapeWords incorporates target 3D shape information within specialized tokens embedded...
0
0
1
SpotLight: Shadow-Guided Object Relighting via Diffusion.
arxiv.org
Recent work has shown that diffusion models can serve as powerful neural rendering engines that can be leveraged for inserting virtual objects into images. However, unlike typical physics-based...
0
0
1
RectifiedHR: High-Resolution Diffusion via Energy Profiling and Adaptive Guidance Scheduling.
arxiv.org
High-resolution image synthesis with diffusion models often suffers from energy instabilities and guidance artifacts that degrade visual quality. We analyze the latent energy landscape during...
0
0
0
What matters for Representation Alignment: Global Information or Spatial Structure?.
arxiv.org
Representation alignment (REPA) guides generative training by distilling representations from a strong, pretrained vision encoder to intermediate diffusion features. We investigate a fundamental...
0
0
0
DeMapGS: Simultaneous Mesh Deformation and Surface Attribute Mapping via Gaussian Splatting.
arxiv.org
We propose DeMapGS, a structured Gaussian Splatting framework that jointly optimizes deformable surfaces and surface-attached 2D Gaussian splats. By anchoring splats to a deformable template mesh,...
0
0
1
Neural Hamiltonian Deformation Fields for Dynamic Scene Rendering.
arxiv.org
Representing and rendering dynamic scenes with complex motions remains challenging in computer vision and graphics. Recent dynamic view synthesis methods achieve high-quality rendering but often...
0
0
1
HOLE: Homological Observation of Latent Embeddings for Neural Network Interpretability.
arxiv.org
Deep learning models have achieved remarkable success across various domains, yet their learned representations and decision-making processes remain largely opaque and hard to interpret. This work...
0
0
0
Foveation Improves Payload Capacity in Steganography.
0
0
0
MACS: Multi-source Audio-to-image Generation with Contextual Significance and Semantic Alignment.
arxiv.org
Propelled by the breakthrough in deep generative models, audio-to-image generation has emerged as a pivotal cross-modal task that converts complex auditory signals into rich visual...
0
0
0
Im2SurfTex: Surface Texture Generation via Neural Backprojection of Multi-View Images.
arxiv.org
We present Im2SurfTex, a method that generates textures for input 3D shapes by learning to aggregate multi-view image outputs produced by 2D image diffusion models onto the shapes' texture space....
0
0
3
GTAvatar: Bridging Gaussian Splatting and Texture Mapping for Relightable and Editable Gaussian Avatars.
arxiv.org
Recent advancements in Gaussian Splatting have enabled increasingly accurate reconstruction of photorealistic head avatars, opening the door to numerous applications in visual effects,...
0
0
0
AI Co-Artist: A LLM-Powered Framework for Interactive GLSL Shader Animation Evolution.
arxiv.org
Creative coding and real-time shader programming are at the forefront of interactive digital art, enabling artists, designers, and enthusiasts to produce mesmerizing, complex visual effects that...
0
1
2
Residual Primitive Fitting of 3D Shapes with SuperFrusta.
arxiv.org
We introduce a framework for converting 3D shapes into compact and editable assemblies of analytic primitives, directly addressing the persistent trade-off between reconstruction fidelity and...
0
0
3
A General Approach to Visualizing Uncertainty in Statistical Graphics.
arxiv.org
Visualizing uncertainty is integral to data analysis, yet its application is often hindered by the need for specialized methods for quantifying and representing uncertainty for different types of...
0
0
0
Neural Radiance Fields for the Real World: A Survey.
arxiv.org
Neural Radiance Fields (NeRFs) have remodeled 3D scene representation since release. NeRFs can effectively reconstruct complex 3D scenes from 2D images, advancing different fields and applications...
0
1
3
Deep Learning, Machine Learning -- Digital Signal and Image Processing: From Theory to Application.
arxiv.org
Digital Signal Processing (DSP) and Digital Image Processing (DIP) with Machine Learning (ML) and Deep Learning (DL) are popular research areas in Computer Vision and related fields. We highlight...
0
0
0
Spec-Gloss Surfels and Normal-Diffuse Priors for Relightable Glossy Objects.
arxiv.org
Accurate reconstruction and relighting of glossy objects remain a longstanding challenge, as object shape, material properties, and illumination are inherently difficult to disentangle. Existing...
0
0
2