Results 91 to 100 of about 8,361,437 (204)

Layer3D: A 3D Layered Representation for Multiview Vector Graphics

Computer Graphics Forum, EarlyView.
Abstract We present Layer3D, a novel 3D neural representation that models objects as collections of decomposable neural implicit primitives. These primitives enable the generation of layered images with consistent correspondences across viewpoints, establishing a flexible framework for multiview vector graphics decomposition.
Zhongyue Guan, Yixin Hu, Zeyu Wang
wiley   +1 more source

The Truth, the Whole Truth, and Nothing but the Truth: Automatic Visualization Evaluation from Reconstruction Quality

Computer Graphics Forum, EarlyView.
Abstract Recent advances in AI enable the automatic generation of visualizations directly from textual prompts using agentic workflows. However, visualizations produced via one‐shot generative methods often suffer from insufficient quality, typically requiring a human in the loop to refine the outputs.
Roxana Bujack, Li‐Ta Lo, Ethan Stam, Ayan Biswas, David Rogers   +4 more
wiley   +1 more source

Single Line Drawing Generation via Semantics‐Driven Optimization

Computer Graphics Forum, EarlyView.
We present a method for automatically generating single‐line drawings in vector format, guided by a text prompt or an input image. Our approach leverages score distillation sampling to optimize the parameters of a uniform rational B‐spline (URBS) curve, ensuring that the drawing consists of a single continuous stroke by design.
Tanguy Magne, Alexandre Binninger, Ruben Wiersma, Olga Sorkine‐Hornung   +3 more
wiley   +1 more source

ER-NeRF++: Efficient region-aware Neural Radiance Fields for high-fidelity talking portrait synthesis

Despite conditional Neural Radiance Fields (NeRF) achieving great success in modeling audio-driven talking portraits, the generation quality is increasingly hampered by the lack of efficient use of space information.
Gu, L, Li, J, Zhou, J, Bai, X, Zheng, J, Zhang, J   +5 more
core   +1 more source

FlowGS: Controlling Information Flow for Graph‐Based Interaction in 3D Gaussian Splatting

Computer Graphics Forum, EarlyView.
Abstract 3D Gaussian Splatting (3DGS) has recently enabled real‐time, high‐quality novel view synthesis. However, its formulation treats each Gaussian independently, lacking explicit information exchange between neighboring elements and limiting its ability to capture local structure.
T. Jia, R. Sun, W. Shi
wiley   +1 more source

Evaluating Neural Radiance Fields for 3D Plant Geometry Reconstruction in Field Conditions

Plant Phenomics
We evaluate different Neural Radiance Field (NeRF) techniques for the 3D reconstruction of plants in varied environments, from indoor settings to outdoor fields.
Muhammad Arbab Arshad, Talukder Jubery, James Afful, Anushrut Jignasu, Aditya Balu, Baskar Ganapathysubramanian, Soumik Sarkar, Adarsh Krishnamurthy   +7 more
doaj   +1 more source

Advances in 4D Representation: Geometry, Motion, and Interaction

Computer Graphics Forum, EarlyView.
We survey 4D representation through three key pillars — geometry, motion, and interaction — offering a selective, representation‐centric perspective to guide researchers in choosing and customizing the right 4D representation for their tasks. Abstract We present a survey on 4D generation and reconstruction, a fast‐evolving subfield of computer graphics
M. Zhao, S. Nag, K. Wang, A. Vora, G. Ji, P. Chun, A. Mahdavi‐Amiri, H. Zhang   +7 more
wiley   +1 more source

ProNeRF: Learning Efficient Projection-Aware Ray Sampling for Fine-Grained Implicit Neural Radiance Fields

IEEE Access
Recent advances in neural rendering have shown that although computationally expensive and slow for training, implicit compact models can accurately learn a scene’s geometries and view-dependent appearances from multiple views.
Juan Luis Gonzalez Bello, Minh-Quan Viet Bui, Munchurl Kim   +2 more
doaj   +1 more source

KPI‐NeRF: Hyperspectral Neural Radiance Fields from a Single Kaleidoscopic Plenoptic Image

Computer Graphics Forum, EarlyView.
KPI‐NeRF reconstructs hyperspectral light field images from a single kaleidoscopic plenoptic image. By leveraging neural radiance fields, it enables high‐quality spectral and angular de‐multiplexing for dynamic scene capture. Abstract Plenoptic imaging has excessive sampling requirements associated with the high dimensionality of the desired data.
Erqi Huang, John Restrepo, Xun Cao, Ivo Ihrke   +3 more
wiley   +1 more source

Recent Trends in Inverse Rendering

Computer Graphics Forum, EarlyView.
This survey reviews 84 papers published between 2020 and 2025 on inverse rendering methods, introducing a taxonomy based on input data, scene representations, optimization strategies, and evaluation methods. We analyze emerging trends in neural, differentiable, and Gaussian‐splatting approaches, discuss applications, and identify key challenges and ...
S. Ullah, F. Pellacini, A. Giachetti
wiley   +1 more source