Search Results - "Computing methodologies → Image‐based rendering"

Deep Video‐Based Performance Cloning by Aberman, K., Shi, M., Liao, J., Liscbinski, D., Chen, B., Cohen‐Or, D.

“…We present a new video‐based performance cloning technique. After training a deep generative network using a reference video capturing the appearance and…”
Get full text

NoPe‐NeRF++: Local‐to‐Global Optimization of NeRF with No Pose Prior by Shi, Dongbo, Cao, Shen, Wu, Bojian, Guo, Jinhui, Fan, Lubin, Chen, Renjie, Liu, Ligang, Ye, Jieping

“…In this paper, we introduce NoPe‐NeRF++, a novel local‐to‐global optimization algorithm for training Neural Radiance Fields (NeRF) without requiring pose…”
Get full text

Perceptual Quality Assessment of NeRF and Neural View Synthesis Methods for Front‐Facing Views by Liang, H., Wu, T., Hanji, P., Banterle, F., Gao, H., Mantiuk, R., Öztireli, C.

“…Neural view synthesis (NVS) is one of the most successful techniques for synthesizing free viewpoint videos, capable of achieving high fidelity from only a…”
Get full text

Does 3D Gaussian Splatting Need Accurate Volumetric Rendering? by Celarek, A., Kopanas, G., Drettakis, G., Wimmer, M., Kerbl, B.

“…Since its introduction, 3D Gaussian Splatting (3DGS) has become an important reference method for learning 3D representations of a captured scene, allowing…”
Get full text

ClothingTwin: Reconstructing Inner and Outer Layers of Clothing Using 3D Gaussian Splatting by Jung, Munkyung, Lee, Dohae, Lee, In‐Kwon

“…We introduce ClothingTwin, a novel end‐to‐end framework for reconstructing 3D digital twins of clothing that capture both the outer and inner fabric —without…”
Get full text

GS‐Octree: Octree‐based 3D Gaussian Splatting for Robust Object‐level 3D Reconstruction Under Strong Lighting by Li, J., Wen, Z., Zhang, L., Hu, J., Hou, F., Zhang, Z., He, Y.

“…The 3D Gaussian Splatting technique has significantly advanced the construction of radiance fields from multi‐view images, enabling real‐time rendering. While…”
Get full text

D‐NPC: Dynamic Neural Point Clouds for Non‐Rigid View Synthesis from Monocular Video by Kappel, Moritz, Hahlbohm, Florian, Scholz, Timon, Castillo, Susana, Theobalt, Christian, Eisemann, Martin, Golyanik, Vladislav, Magnor, Marcus

“…Dynamic reconstruction and spatiotemporal novel‐view synthesis of non‐rigidly deforming scenes recently gained increased attention. While existing work…”
Get full text

PVP: Personalized Video Prior for Editable Dynamic Portraits using StyleGAN by Lin, K.‐E., Trevithick, A., Cheng, K., Sarkis, M., Ghafoorian, M., Bi, N., Reitmayr, G., Ramamoorthi, R.

“…Portrait synthesis creates realistic digital avatars which enable users to interact with others in a compelling way. Recent advances in StyleGAN and its…”
Get full text

GauLoc: 3D Gaussian Splatting‐based Camera Relocalization by Xin, Zhe, Dai, Chengkai, Li, Ying, Wu, Chenming

“…3D Gaussian Splatting (3DGS) has emerged as a promising representation for scene reconstruction and novel view synthesis for its explicit representation and…”
Get full text

CP‐NeRF: Conditionally Parameterized Neural Radiance Fields for Cross‐scene Novel View Synthesis by He, Hao, Liang, Yixun, Xiao, Shishi, Chen, Jierun, Chen, Yingcong

“…Neural radiance fields (NeRF) have demonstrated a promising research direction for novel view synthesis. However, the existing approaches either require…”
Get full text

Interactive Control over Temporal Consistency while Stylizing Video Streams by Shekhar, Sumit, Reimann, Max, Hilscher, Moritz, Semmo, Amir, Döllner, Jürgen, Trapp, Matthias

“…Image stylization has seen significant advancement and widespread interest over the years, leading to the development of a multitude of techniques. Extending…”
Get full text

Image‐Based Spatio‐Temporal Interpolation for Split Rendering by Steiner, M., Köhler, T., Radl, L., Budge, B., Steinberger, M.

“…Low‐powered devices – such as small form factor head‐mounted displays (HMDs) – struggle to deliver a smooth and high‐quality viewing experience, due to their…”
Get full text

Deep Flow Rendering: View Synthesis via Layer‐aware Reflection Flow by Dai, Pinxuan, Xie, Ning

“…Novel view synthesis (NVS) generates images from unseen viewpoints based on a set of input images. It is a challenge because of inaccurate lighting…”
Get full text

RGB2AO: Ambient Occlusion Generation from RGB Images by Inoue, N., Ito, D., Hold‐Geoffroy, Y., Mai, L., Price, B., Yamasaki, T.

“…We present RGB2AO, a novel task to generate ambient occlusion (AO) from a single RGB image instead of screen space buffers such as depth and normal. RGB2AO…”
Get full text

HMLFC: Hierarchical Motion‐Compensated Light Field Compression for Interactive Rendering by Pratapa, S., Manocha, D.

“…We present a new motion‐compensated hierarchical compression scheme (HMLFC) for encoding light field images (LFI) that is suitable for interactive rendering…”
Get full text

Image‐Based Tree Variations by Argudo, Oscar, Andújar, Carlos, Chica, Antoni

“…The automatic generation of realistic vegetation closely reproducing the appearance of specific plant species is still a challenging topic in computer…”
Get full text

Interactive Photo Editing on Smartphones via Intrinsic Decomposition by Shekhar, Sumit, Reimann, Max, Mayer, Maximilian, Semmo, Amir, Pasewaldt, Sebastian, Döllner, Jürgen, Trapp, Matthias

“…Intrinsic decomposition refers to the problem of estimating scene characteristics, such as albedo and shading, when one view or multiple views of a scene are…”
Get full text

An AR-Guided System for Fast Image-Based Modeling of Indoor Scenes by Andersen, Daniel, Popescu, Voicu

“…We present a system that enables a novice user to acquire a large indoor scene in minutes as a collection of images that are sufficient for five…”
Get full text

PatchNeRF: Patch-based Neural Radiance Fields for real time view synthesis in wide-scale scenes by Hu, Ziyu, Jiang, Xiaoguang, Liu, Qiong, Ding, Xin

“…Recent methods based on Neural Radiance Fields (NeRFs) have excelled in real-time novel view synthesis for small-scale scenes but struggle with fast rendering…”
Get full text

SPIDER: A framework for processing, editing and presenting immersive high-resolution spherical indoor scenes by Tukur, M., Pintore, G., Gobbetti, E., Schneider, J., Agus, M.

“…Today’s Extended Reality (XR) applications that call for specific Diminished Reality (DR) strategies to hide specific classes of objects are increasingly using…”
Get full text