Results 31 to 40 of about 3,318,906 (295)

Complex-Motion NeRF: Joint Reconstruction and Pose Optimization With Motion and Depth Priors

IEEE Access, 2023
We present Complex-Motion Neural Radiance Fields (CM-NeRF), which is a method that leverages motion and depth priors to optimize neural 3D scene representations and complex 6-DoF camera motions jointly.
Hyunjin Kim, Daekyeong Lee, Suyoung Kang, Pyojin Kim   +3 more
doaj   +1 more source

Reinforcement Learning with Neural Radiance Fields

Advances in Neural Information Processing Systems 35, 2022
It is a long-standing problem to find effective representations for training reinforcement learning (RL) agents. This paper demonstrates that learning state representations with supervision from Neural Radiance Fields (NeRFs) can improve the performance of RL compared to other learned representations or even low-dimensional, hand-engineered state ...
Danny Driess, Ingmar Schubert, Peter R. Florence, Yunzhu Li, Marc Toussaint   +4 more
openaire   +4 more sources

CoNeRF: Controllable Neural Radiance Fields

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2022
We extend neural 3D representations to allow for intuitive and interpretable user control beyond novel view rendering (i.e. camera control). We allow the user to annotate which part of the scene one wishes to control with just a small number of mask annotations in the training images. Our key idea is to treat the attributes as latent variables that are
Kacper Kania, Kwang Moo Yi, Marek Kowalski, Tomasz Trzcinski, Andrea Tagliasacchi   +4 more
openaire   +3 more sources

SegNeRF: 3D Part Segmentation with Neural Radiance Fields [PDF]

, 2022
Recent advances in Neural Radiance Fields (NeRF) boast impressive performances for generative tasks such as novel view synthesis and 3D reconstruction.
Zarzar, Jesus, Rojas, Sara, Giancola, Silvio, Ghanem, Bernard   +3 more
core   +1 more source

SPARSESAT-NERF: DENSE DEPTH SUPERVISED NEURAL RADIANCE FIELDS FOR SPARSE SATELLITE IMAGES [PDF]

ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, 2023
Digital surface model generation using traditional multi-view stereo matching (MVS) performs poorly over non-Lambertian surfaces, with asynchronous acquisitions, or at discontinuities. Neural radiance fields (NeRF) offer a new paradigm for reconstructing
L. Zhang, L. Zhang, E. Rupnik
doaj   +1 more source

Self-Evolving Neural Radiance Fields

CoRR, 2023
Recently, neural radiance field (NeRF) has shown remarkable performance in novel view synthesis and 3D reconstruction. However, it still requires abundant high-quality images, limiting its applicability in real-world scenarios. To overcome this limitation, recent works have focused on training NeRF only with sparse viewpoints by giving additional ...
Jaewoo Jung, Jisang Han, Jiwon Kang, Seongchan Kim, Minseop Kwak, Seungryong Kim   +5 more
openaire   +3 more sources

NeRFUS: neural radiance fields with uncertainty and semantics [PDF]

PeerJ Computer Science
In recent years, significant progress has been made in the differentiable representation of three-dimensional scenes using neural radiance fields (NeRFs). These models can effectively synthesize novel views containing color information or semantic masks;
Egor Zubkov, Darya Drozdova, Dmitry Yudin   +2 more
doaj   +2 more sources

Deformable Neural Radiance Fields using RGB and Event Cameras [PDF]

, 2023
Modeling Neural Radiance Fields for fast-moving deformable objects from visual data alone is a challenging problem. A major issue arises due to the high deformation and low acquisition rates.
Ma, Qi, Paudel, Danda Pani, Chhatkuli, Ajad, Van Gool, Luc   +3 more
core  

ShinyNeRF: Digitizing Anisotropic Appearance in Neural Radiance Fields [PDF]

The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences
Recent advances in digitization technologies have transformed the preservation and dissemination of cultural heritage. In this vein, Neural Radiance Fields (NeRF) have emerged as a leading technology for 3D digitization, delivering representations with ...
A. Barreiro, A. Barreiro, R. Marí, R. Redondo, G. Haro, C. Bosch   +5 more
doaj   +1 more source

Cascaded and Generalizable Neural Radiance Fields for Fast View Synthesis

, 2023
We present CG-NeRF, a cascade and generalizable neural radiance fields method for view synthesis. Recent generalizing view synthesis methods can render high-quality novel views using a set of nearby input views. However, the rendering speed is still slow
Rahtu, Esa, Nguyen-Ha, Phong, Huynh, Lam, Matas, Jiri, Heikkilä, Janne   +4 more
core   +1 more source